Hybrid Arima - LSTM code - Full Dataset¶

The hybrid ARIMA-LSTM model is open to a variety of experimentation. For ideal performance, a balance must be reached between the levels of volatility that work best for the ARIMA and LSTM models. Using shorter MA periods that result in a non-mesokurtic distribution may achieve a better volatility balance between models.

Import Libraries¶

import pandas as pd
pd.set_option('display.max_rows', 500)
import timeit

!pip install -q -U keras-tuner

     |████████████████████████████████| 98 kB 4.1 MB/s

import keras_tuner as kt

!pip install pmdarima

Collecting pmdarima
  Downloading pmdarima-1.8.4-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.manylinux_2_24_x86_64.whl (1.4 MB)
     |████████████████████████████████| 1.4 MB 5.1 MB/s 
Collecting statsmodels!=0.12.0,>=0.11
  Downloading statsmodels-0.13.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (9.8 MB)
     |████████████████████████████████| 9.8 MB 28.3 MB/s 
Requirement already satisfied: pandas>=0.19 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (1.1.5)
Requirement already satisfied: urllib3 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (1.24.3)
Requirement already satisfied: setuptools!=50.0.0,>=38.6.0 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (57.4.0)
Requirement already satisfied: numpy>=1.19.3 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (1.19.5)
Requirement already satisfied: scipy>=1.3.2 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (1.4.1)
Requirement already satisfied: scikit-learn>=0.22 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (1.0.1)
Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (1.1.0)
Requirement already satisfied: Cython!=0.29.18,>=0.29 in /usr/local/lib/python3.7/dist-packages (from pmdarima) (0.29.24)
Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.7/dist-packages (from pandas>=0.19->pmdarima) (2018.9)
Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.7/dist-packages (from pandas>=0.19->pmdarima) (2.8.2)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.7/dist-packages (from python-dateutil>=2.7.3->pandas>=0.19->pmdarima) (1.15.0)
Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from scikit-learn>=0.22->pmdarima) (3.0.0)
Requirement already satisfied: patsy>=0.5.2 in /usr/local/lib/python3.7/dist-packages (from statsmodels!=0.12.0,>=0.11->pmdarima) (0.5.2)
Installing collected packages: statsmodels, pmdarima
  Attempting uninstall: statsmodels
    Found existing installation: statsmodels 0.10.2
    Uninstalling statsmodels-0.10.2:
      Successfully uninstalled statsmodels-0.10.2
Successfully installed pmdarima-1.8.4 statsmodels-0.13.1

import pmdarima

url = 'https://launchpad.net/~mario-mariomedina/+archive/ubuntu/talib/+files'
!wget $url/libta-lib0_0.4.0-oneiric1_amd64.deb -qO libta.deb
!wget $url/ta-lib0-dev_0.4.0-oneiric1_amd64.deb -qO ta.deb
!dpkg -i libta.deb ta.deb
!pip install ta-lib
import talib

Selecting previously unselected package libta-lib0.
(Reading database ... 155222 files and directories currently installed.)
Preparing to unpack libta.deb ...
Unpacking libta-lib0 (0.4.0-oneiric1) ...
Selecting previously unselected package ta-lib0-dev.
Preparing to unpack ta.deb ...
Unpacking ta-lib0-dev (0.4.0-oneiric1) ...
Setting up libta-lib0 (0.4.0-oneiric1) ...
Setting up ta-lib0-dev (0.4.0-oneiric1) ...
Processing triggers for man-db (2.8.3-2ubuntu0.1) ...
Processing triggers for libc-bin (2.27-3ubuntu1.3) ...
/sbin/ldconfig.real: /usr/local/lib/python3.7/dist-packages/ideep4py/lib/libmkldnn.so.0 is not a symbolic link

Collecting ta-lib
  Downloading TA-Lib-0.4.22.tar.gz (268 kB)
     |████████████████████████████████| 268 kB 5.2 MB/s 
  Installing build dependencies ... done
  Getting requirements to build wheel ... done
    Preparing wheel metadata ... done
Requirement already satisfied: numpy in /usr/local/lib/python3.7/dist-packages (from ta-lib) (1.19.5)
Building wheels for collected packages: ta-lib
  Building wheel for ta-lib (PEP 517) ... done
  Created wheel for ta-lib: filename=TA_Lib-0.4.22-cp37-cp37m-linux_x86_64.whl size=1465698 sha256=e0ee59ea3a3a2be9f8d64677fdd5cc7390a01e917590faa1e5d572749cb1727b
  Stored in directory: /root/.cache/pip/wheels/7b/63/a9/144081748d9c4f0a09b4670c7b3c414bcb33ff97f0724c753a
Successfully built ta-lib
Installing collected packages: ta-lib
Successfully installed ta-lib-0.4.22

import tensorflow
import statsmodels.tsa.api
import keras
import sklearn

from tensorflow.keras.optimizers import Adam
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Dense, LSTM, Dropout, Bidirectional,BatchNormalization, Embedding, TimeDistributed, LeakyReLU, GRU
from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint, ReduceLROnPlateau

from keras.models import Sequential, load_model
from keras.layers import Dense, LSTM, Activation, Dropout
from keras import backend as K
from keras.utils.generic_utils import get_custom_objects
from keras.callbacks import ModelCheckpoint,EarlyStopping
from keras.regularizers import l1_l2

import math

from statsmodels.tsa.api import VAR
from statsmodels.tsa.statespace.varmax import VARMAX,VARMAXResults

from sklearn.metrics import mean_squared_error, mean_absolute_percentage_error, mean_absolute_error
from sklearn.preprocessing import MinMaxScaler
from sklearn.model_selection import train_test_split

from matplotlib import pyplot

import json
import datetime
import pandas as pd
import numpy as np
import os
from scipy.stats import kurtosis
import pmdarima as pm
from pmdarima import auto_arima
from talib import abstract
import json
import matplotlib.pyplot as plt
# plt.rcParams.update({'font.size': 16})
from matplotlib.pyplot import figure
from numpy import array
from numpy import hstack
from keras.models import Sequential
from keras.layers import LSTM
from keras.layers import Dense
from keras.layers import RepeatVector
from keras.layers import TimeDistributed

from keras.utils.generic_utils import get_custom_objects
from tensorflow.keras.utils import plot_model

import warnings
from statsmodels.tools.sm_exceptions import ConvergenceWarning
warnings.simplefilter('ignore', ConvergenceWarning)

Reference 1: https://towardsdatascience.com/time-series-forecasting-predicting-stock-prices-using-an-arima-model-2e3b3080bd70

Load Data¶

from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive

cd drive/MyDrive/Stock price prediction/Generated datasets

/content/drive/.shortcut-targets-by-id/1IaGjVBlTspxI2CHSrxfYnaiYvsaG0pHs/Stock price prediction/Generated datasets

df = pd.read_csv("FULL_Data_google_COVID_bull_bear.csv",parse_dates=[0])
df.tail(10)

ls

shell-init: error retrieving current directory: getcwd: cannot access parent directories: No such file or directory
'AG Project NB'/
'Akshada Notebooks'/
'Archana - LSTM Hybrid'/
 dataset_final_tech_ind_sentiment_score.csv
 DL_FinalProject_GoogleTrends_Akshada.ipynb
"Experiment NB's"/
'Generated datasets'/
'PLOTS Akshada'/
 Reports/
 results_updated.xlsx
 results.xlsx
'Stock Closing Price Prediction.pptx'
 Stocks/
'Training data'/

cd Archana - LSTM Hybrid/Outputs/full

/content/drive/.shortcut-targets-by-id/1IaGjVBlTspxI2CHSrxfYnaiYvsaG0pHs/Stock price prediction/Archana - LSTM Hybrid/Outputs/full

pd.to_datetime(df[np.isnan(df.Close)==True]['Date']).dt.day_name().head(5)

0    Saturday
1      Sunday
3     Tuesday
7    Saturday
8      Sunday
Name: Date, dtype: object

len(pd.to_datetime(df[np.isnan(df.Close)==True]['Date']).dt.day_name())

497

len(df)

1602

len(df) - len(pd.to_datetime(df[np.isnan(df.Close)==True]['Date']).dt.day_name())

1105

df.dropna(inplace=True)
len(df)

1080

pd.to_datetime(df[np.isnan(df.Close)==True]['Date']).dt.day_name()

Series([], Name: Date, dtype: object)

df.head(5)

stock_col= list(df.columns)
stock_col = stock_col[4:len(stock_col)]

dataset_final = df[stock_col]

dataset_final.head(5)

Data Load for Experiments with Fulldata¶

# stock_col= list(df.columns)
# stock_col1 = stock_col[4:len(stock_col)-9]
# stock_col2 = stock_col[len(stock_col)-7:len(stock_col)]
# stock_col1.append(stock_col2)
# dataset_final = df
dataset_final.head(5)

# Set the date to datetime data
datetime_series = pd.to_datetime(dataset_final['Date'])
datetime_index = pd.DatetimeIndex(datetime_series.values)
dataset_final = dataset_final.set_index(datetime_index)
dataset_final = dataset_final.sort_values(by='Date')
dataset_final = dataset_final.drop(columns='Date')
dataset_final.head(5)

Train & test Dataset for Multistep Process¶

# Get features and target
X_value = pd.DataFrame(dataset_final.iloc[:, :])
y_value = pd.DataFrame(dataset_final.iloc[:, 3])

y_value.head(5)

# Normalized the data
X_scaler = MinMaxScaler(feature_range=(-1, 1))
y_scaler = MinMaxScaler(feature_range=(-1, 1))
X_scaler.fit(X_value)
y_scaler.fit(y_value)

MinMaxScaler(feature_range=(-1, 1))

X_scale_dataset = X_scaler.fit_transform(X_value)
y_scale_dataset = y_scaler.fit_transform(y_value)

X_scale_dataset.shape, y_scale_dataset.shape,

((1080, 29), (1080, 1))

X_value.shape[1]

29

N Steps Definition¶

n_steps_in = 3
n_features = X_value.shape[1] #19 features
n_steps_out = 1

# Reshape the data
'''Set the data input steps and output steps, 
    we use 30 days data to predict 1 day price here, 
    reshape it to (None, input_step, number of features) used for LSTM input'''
# Get X/y dataset
def get_X_y(X_data, y_data):
    X = list()
    y = list()
    yc = list()

    length = len(X_data)
    for i in range(0, length, 1):
        # pdb.set_trace()
        X_value = X_data[i: i + n_steps_in][:, :]
        # print('[',i,': ',i,' + ',n_steps_in,'][:, :]')
        y_value = y_data[i + n_steps_in: i + (n_steps_in + n_steps_out)][:, 0]
        # print('[',i,' + ',n_steps_in,': ',i,' + (',n_steps_in,' + ',n_steps_out,')][:, 0]')
        yc_value = y_data[i: i + n_steps_in][:, :]
        if len(X_value) == 3 and len(y_value) == 1:
            X.append(X_value)
            y.append(y_value)
            yc.append(yc_value)

    return np.array(X), np.array(y), np.array(yc)

# get the train test predict index
def predict_index(dataset, X_train, n_steps_in, n_steps_out):

    # get the predict data (remove the in_steps days)
    train_predict_index = dataset.iloc[n_steps_in : X_train.shape[0] + n_steps_in + n_steps_out - 1, :].index
    test_predict_index = dataset.iloc[X_train.shape[0] + n_steps_in:, :].index

    return train_predict_index, test_predict_index

def mean_absolute_percentage_error(actual, prediction):
    actual = pd.Series(actual)
    prediction = pd.Series(prediction)
    return 100 * np.mean(np.abs((actual - prediction))/actual)

# Split train/test dataset
def split_train_test(data):
    train_size = round(len(X) * 0.75)
    data_train = data[0:train_size]
    data_test = data[train_size:]
    return data_train, data_test

# Get data and check shape
X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
# pdb.set_trace()
X_train, X_test, = split_train_test(X)
y_train, y_test, = split_train_test(y)
yc_train, yc_test, = split_train_test(yc)
index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)

# %% --------------------------------------- Save dataset -----------------------------------------------------------------
print('X shape: ', X.shape)
print('y shape: ', y.shape)
print('X_train shape: ', X_train.shape)
print('y_train shape: ', y_train.shape)
print('y_c_train shape: ', yc_train.shape)
print('X_test shape: ', X_test.shape)
print('y_test shape: ', y_test.shape)
print('y_c_test shape: ', yc_test.shape)
print('index_train shape:', index_train.shape)
print('index_test shape:', index_test.shape)

X shape:  (1077, 3, 29)
y shape:  (1077, 1)
X_train shape:  (808, 3, 29)
y_train shape:  (808, 1)
y_c_train shape:  (808, 3, 1)
X_test shape:  (269, 3, 29)
y_test shape:  (269, 1)
y_c_test shape:  (269, 3, 1)
index_train shape: (808,)
index_test shape: (269,)

output_dim = y_train.shape[1]
output_dim

1

df = dataset_final.copy()

df.rename(columns={'Date':'date','Open':'open','Low':'low','Close':'close','Volume':'volume','High':'high'}, inplace = True)
df.reset_index(drop=True,inplace=True)

df.head(1)

# df.drop(['volume', 'MACD','20SD','logmomentum','absolute of 3 comp','angle of 3 comp','absolute of 6 comp','angle of 6 comp','absolute of 9 comp','angle of 9 comp'], axis='columns', inplace=True) # only keep columns that can help as residuals in Arima Hybrid

df.head(1)

Train & Test Length¶

test_len = len(X_test)

train_len = len(X_train )

test_len, train_len

(269, 808)

Kurtosis Review¶

# Initialize moving averages from Ta-Lib, store functions in dictionary
# talib_moving_averages = ['SMA', 'EMA', 'WMA', 'DEMA', 'KAMA', 'MIDPOINT', 'MIDPRICE', 'T3', 'TEMA', 'TRIMA'] remove midprice due to outputbeing univariate
talib_moving_averages = ['SMA', 'EMA', 'WMA', 'DEMA', 'KAMA', 'MIDPOINT',  'T3', 'TEMA', 'TRIMA'] 
functions = {}
for ma in talib_moving_averages:
      functions[ma] = abstract.Function(ma)

    # Determine kurtosis "K" values for MA period 4-30
kurtosis_results = {'period': []}
for i in range(4, 100): # 100
  kurtosis_results['period'].append(i)
  for ma in talib_moving_averages:
              # Run moving average, remove last N days (used later for test data set), trim MA result to last 30 days
              ma_output = functions[ma](df[:-test_len], i).tail(14)
              # Determine kurtosis "K" value
              k = kurtosis(ma_output, fisher=False)
              # add to dictionary
              if ma not in kurtosis_results.keys():
                  kurtosis_results[ma] = []
              kurtosis_results[ma].append(k)

kurtosis_results = pd.DataFrame(kurtosis_results)
kurtosis_results.to_csv('kurtosis_results.csv')

kurtosis_results.head(5)

Optimized periods¶

# Determine period with K closest to 3 +/-5%
optimized_period = {}
# https://pypi.org/project/TA-Lib/ determines the type of moving average to use
# https://pandas.pydata.org/pandas-docs/version/0.17.0/generated/pandas.DataFrame.at.html#pandas.DataFrame.at
for ma in talib_moving_averages:
        difference = np.abs(kurtosis_results[ma] - 3)
        df_arimahyb = pd.DataFrame({'difference': difference, 'period': kurtosis_results['period']})
        df_arimahyb = df_arimahyb.sort_values(by=['difference'], ascending=True).reset_index(drop=True)
        if df_arimahyb.at[0, 'difference'] < 3 * 0.05:
            optimized_period[ma] = df_arimahyb.at[0, 'period']
        else:
            print(ma + ' is not viable, best K greater or less than 3 +/-5%')

print('\nOptimized periods:', optimized_period)

TRIMA is not viable, best K greater or less than 3 +/-5%

Optimized periods: {'SMA': 17, 'EMA': 51, 'WMA': 49, 'DEMA': 89, 'KAMA': 18, 'MIDPOINT': 14, 'T3': 19, 'TEMA': 9}

optimized_period

{'DEMA': 89,
 'EMA': 51,
 'KAMA': 18,
 'MIDPOINT': 14,
 'SMA': 17,
 'T3': 19,
 'TEMA': 9,
 'WMA': 49}

Simulation Keys¶

simulation = {}
for ma in optimized_period:
        print(ma)
        print(functions[ma])
        print ( int( optimized_period[ma]))
        # if ma in ['EMA','WMA','DEMA','KAMA','MIDPOINT']:
        #   print(ma)
        low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
        low_vol = low_vol.fillna(0)
        high_vol = pd.DataFrame()
        df2 = df.copy()
        for i in df2.columns:
          if i in low_vol.columns:
            high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9

low_vol.tail(20)

high_vol.head(10)

Common Functions¶

def get_arima(dataframe,original_data, train_len, test_len):
    # prepare train and test data
    X_value = pd.DataFrame(dataframe.iloc[:, :])
    y_value = pd.DataFrame(dataframe.iloc[:, 3])
    X_train, X_test = split_train_test(X_value)
    y_train, y_test = split_train_test(y_value)
    yc_train,yc_test = split_train_test(original_data)
    # y_train_ = y_train['close'].to_list()
    # y_test_ = y_test['close'].to_list()
    yc = yc_test.values.tolist()
    y_train_list = y_train['close'].values.tolist() 
    y_test_list = y_test['close'].values.tolist()                                           
      
    # Initialize model
    model = auto_arima(y_train_list,trace=True, error_action='ignore', start_p=1,start_q=1,max_p=3,max_q=3,d=3,
                  suppress_warnings=True,stepwise=True,seasonal=True)
    print(model.summary())
        # Determine model parameters
    model.fit(y_train_list,disp= 0)
    order = model.get_params()['order']
    print('ARIMA order:', order, '\n')

        # Genereate predictions
    prediction = []
    for i in range(len(y_test_list)):
            model = pmdarima.ARIMA(order=order)
            model.fit(y_train_list,disp= 0)
            # print('working on', i+1, 'of', len(y_test), '-- ' + str(int(100 * (i + 1) / len(y_test))) + '% complete')
            prediction.append(model.predict()[0])
            y_train_list.append(y_test_list[i])

    # Generate error data
    mse = mean_squared_error(yc_test, prediction)
    rmse = mse ** 0.5
    # mape = mean_absolute_percentage_error(pd.Series(yc_test).values.tolist(), pd.Series(predictionte).values.tolist() )
    mae = mean_absolute_error(pd.Series(yc_test).values.tolist() , pd.Series(prediction).values.tolist() )
    return yc, prediction, mse, rmse, mae

def plot_train(simulation,SIM):
  train_predict_index = np.load("index_train_appl.npy", allow_pickle=True)#Dates for train data

  predict_result = pd.DataFrame()
  for i in range(len(simulation[SIM]['final_tr']['prediction'])):
          y_predict = pd.DataFrame(simulation[SIM]['final_tr']['prediction'][i], columns=["predicted_price"],
                                  index=train_predict_index[i:i + output_dim])
          predict_result = pd.concat([predict_result, y_predict], axis=1, sort=False)
          
          #This is a dataframe with each column containing the predicted daily closing price
  real_price = pd.DataFrame()
  for i in range(len(simulation[SIM]['final_tr']['original'])):
          y_train = pd.DataFrame(simulation[SIM]['final_tr']['original'][i], columns=["real_price"],
                                index=train_predict_index[i:i + output_dim])
          real_price = pd.concat([real_price, y_train], axis=1, sort=False)  #This is a dataframe with each column containing the real daily closing price

  predict_result['predicted_mean'] = predict_result.mean(axis=1)#Adding a column with the daily predicted closing price value
  real_price['real_mean'] = real_price.mean(axis=1)#Adding a column with the daily real closing price value
      #
      # Plot the predicted result
  plt.figure(figsize=(16, 8))
  plt.plot(real_price["real_mean"])
  plt.plot(predict_result["predicted_mean"], color='r')
  plt.xlabel("Date")
  plt.ylabel("Stock price")
  plt.legend(("Real price", "Predicted price"), loc="upper left", fontsize=16)
  plt.title(f"The result of Training for {SIM}", fontsize=20)
  plt.show()

      # Calculate RMSE
  predicted = predict_result["predicted_mean"]
  real = real_price["real_mean"]
  RMSE = np.sqrt(mean_squared_error(predicted, real))
  MSE = mean_squared_error(predicted, real)
  MAE = mean_absolute_error(predicted, real)
  print(f"----- Train RMSE for {SIM} -----", RMSE)
  print(f"----- Train_MSE_LSTM for {SIM} -----", MSE)
  print(f"----- Train MAE LSTM for {SIM} -----", MAE)

def plot_test(simulation, SIM):
  test_predict_index = np.load("index_test_appl.npy", allow_pickle=True)#Dates for train data

      # rescaled_real_y = y_scaler.inverse_transform(y_train)#Real closing price data
      # rescaled_predicted_y = y_scaler.inverse_transform(train_yhat)#Predicted closing price data

  predict_result = pd.DataFrame()
  for i in range(len(simulation[SIM]['final']['prediction'])):
          y_predict = pd.DataFrame(simulation[SIM]['final']['prediction'][i], columns=["predicted_price"],
                                  index=test_predict_index[i:i + output_dim])
          predict_result = pd.concat([predict_result, y_predict], axis=1, sort=False)#This is a dataframe with each column containing the predicted daily closing price
      #
  real_price = pd.DataFrame()
  for i in range(len(simulation[SIM]['final']['original'])):
          y_train = pd.DataFrame(simulation[SIM]['final']['original'][i], columns=["real_price"],
                                index=test_predict_index[i:i + output_dim])
          real_price = pd.concat([real_price, y_train], axis=1, sort=False)#This is a dataframe with each column containing the real daily closing price

  predict_result['predicted_mean'] = predict_result.mean(axis=1)#Adding a column with the daily predicted closing price value
  real_price['real_mean'] = real_price.mean(axis=1)#Adding a column with the daily real closing price value
      #
      # Plot the predicted result
  plt.figure(figsize=(16, 8))
  plt.plot(real_price["real_mean"])
  plt.plot(predict_result["predicted_mean"], color='r')
  plt.xlabel("Date")
  plt.ylabel("Stock price")
  plt.legend(("Real price", "Predicted price"), loc="upper left", fontsize=16)
  plt.title(f"The result of Testing for {SIM}", fontsize=20)
  plt.show()

      # Calculate RMSE
  predicted = predict_result["predicted_mean"]
  real = real_price["real_mean"]
  RMSE = np.sqrt(mean_squared_error(predicted, real))
  MSE = mean_squared_error(predicted, real)
  MAE = mean_absolute_error(predicted, real)
  print(f"----- Test RMSE for {SIM}-----", RMSE)
  print(f"----- Test_MSE_LSTM for {SIM}-----", MSE)
  print(f"----- Test_MAE_LSTM for {SIM}-----", MAE)

def plot_train_high(simulation, SIM):
  train_predict_index = np.load("index_test_appl.npy", allow_pickle=True)#Dates for train data

  predict_result = pd.DataFrame()
  for i in range(len(simulation[SIM]['high_vol']['prediction'])):
          y_predict = pd.DataFrame(simulation[SIM]['high_vol']['prediction'][i], columns=["predicted_price"],
                                  index=train_predict_index[i:i + output_dim])
          predict_result = pd.concat([predict_result, y_predict], axis=1, sort=False)
          
          #This is a dataframe with each column containing the predicted daily closing price
  real_price = pd.DataFrame()
  for i in range(len(simulation[SIM]['high_vol']['original'])):
          y_train = pd.DataFrame(simulation[SIM]['high_vol']['original'][i], columns=["real_price"],
                                index=train_predict_index[i:i + output_dim])
          real_price = pd.concat([real_price, y_train], axis=1, sort=False)  #This is a dataframe with each column containing the real daily closing price

  predict_result['predicted_mean'] = predict_result.mean(axis=1)#Adding a column with the daily predicted closing price value
  real_price['real_mean'] = real_price.mean(axis=1)#Adding a column with the daily real closing price value
      #
      # Plot the predicted result
  plt.figure(figsize=(16, 8))
  plt.plot(real_price["real_mean"])
  plt.plot(predict_result["predicted_mean"], color='r')
  plt.xlabel("Date")
  plt.ylabel("Stock price")
  plt.legend(("Real price", "Predicted price"), loc="upper left", fontsize=16)
  plt.title(f"The result of Training for {SIM}", fontsize=20)
  plt.show()

      # Calculate RMSE
  predicted = predict_result["predicted_mean"]
  real = real_price["real_mean"]
  RMSE = np.sqrt(mean_squared_error(predicted, real))
  MSE = mean_squared_error(predicted, real)
  MAE = mean_absolute_error(predicted, real)
  print(f"----- Individual LSTM RMSE for {SIM} -----", RMSE)
  print(f"----- Individual LSTM_MSE_LSTM for {SIM} -----", MSE)
  print(f"----- Individual LSTM MAE LSTM for {SIM} -----", MAE)

def plot_train_low(simulation , SIM):
  train_predict_index = np.load("index_test_appl.npy", allow_pickle=True)#Dates for train data

  predict_result = pd.DataFrame()
  for i in range(len(simulation[SIM]['low_vol']['prediction'])):
          y_predict = pd.DataFrame(simulation[SIM]['low_vol']['prediction'][i], columns=["predicted_price"],
                                  index=train_predict_index[i:i + output_dim])
          predict_result = pd.concat([predict_result, y_predict], axis=1, sort=False)
          
          #This is a dataframe with each column containing the predicted daily closing price
  real_price = pd.DataFrame()
  for i in range(len(simulation[SIM]['low_vol']['original'])):
          y_train = pd.DataFrame(simulation[SIM]['low_vol']['original'][i], columns=["real_price"],
                                index=train_predict_index[i:i + output_dim])
          real_price = pd.concat([real_price, y_train], axis=1, sort=False)  #This is a dataframe with each column containing the real daily closing price

  predict_result['predicted_mean'] = predict_result.mean(axis=1)#Adding a column with the daily predicted closing price value
  real_price['real_mean'] = real_price.mean(axis=1)#Adding a column with the daily real closing price value
      #
      # Plot the predicted result
  plt.figure(figsize=(16, 8))
  plt.plot(real_price["real_mean"])
  plt.plot(predict_result["predicted_mean"], color='r')
  plt.xlabel("Date")
  plt.ylabel("Stock price")
  plt.legend(("Real price", "Predicted price"), loc="upper left", fontsize=16)
  plt.title(f"The result of Training for {SIM}", fontsize=20)
  plt.show()

      # Calculate RMSE
  predicted = predict_result["predicted_mean"]
  real = real_price["real_mean"]
  RMSE = np.sqrt(mean_squared_error(predicted, real))
  MSE = mean_squared_error(predicted, real)
  MAE = mean_absolute_error(predicted, real)
  print(f"-----Arima RMSE for {SIM} -----", RMSE)
  print(f"----- Arima MSE for {SIM} -----", MSE)
  print(f"----- Arima MAE for {SIM} -----", MAE)

import os
os.getcwd()

'/content/drive/.shortcut-targets-by-id/1IaGjVBlTspxI2CHSrxfYnaiYvsaG0pHs/Stock price prediction/Archana - LSTM Hybrid/Outputs/full'

Univariate Arima Multistep MutiVariate LSTM Hybrid Model Experiment 1¶

def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det = 20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # Option 1
    # Set up & fit LSTM RNN
    model = Sequential()
    model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    model.add(Dense(units=64,activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(units=output_dim))
    model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    ## Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()


    # # option 2
    # model = Sequential()
    # model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    # model.add(Dense(64))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 3
    # define custom activation
    # reference: https://github.com/Vaibhav-Sachdeva/Correlation-Coefficient-Prediction-using-ARIMA-LSTM-Hybrid-Model/blob/main/Code/LSTM-ARIMA.ipynb
    # class Double_Tanh(Activation):
    #     def __init__(self, activation, **kwargs):
    #         super(Double_Tanh, self).__init__(activation, **kwargs)
    #         self.__name__ = 'double_tanh'

    # def double_tanh(x):
    #     return (K.tanh(x) * 2)

    # get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
    #     # Model Generation
    # model = Sequential()
    # #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    # model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    # model.add(Dense(1))
    # model.add(Activation(double_tanh))
    # model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(x_train.shape[1], 1)))
    # model.add(LSTM(units=int(lstm_len/2)))
    # model.add(Dense(1, activation='sigmoid'))
    # model.compile(loss='mean_squared_error', optimizer='adam')
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te

if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation1 = {}
    imgfile = 'Experiment1'
    for ma in optimized_period:
              print(ma)
              print(functions[ma])
              print ( int( optimized_period[ma]))
            # if ma == 'SMA':
              low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
              low_vol = low_vol.fillna(0)
              low_vol_data = df['close']
              high_vol = pd.DataFrame()
              df2 = df.copy()
              for i in df2.columns:
                if i in low_vol.columns:
                  high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
              high_vol_data = df['close']
              ## *****************************************************
              # Generate ARIMA and LSTM predictions
              print('\nWorking on ' + ma + ' predictions')
              try:
                print('parameters used : ', train_len, test_len)
                low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima(low_vol,low_vol_data, train_len, test_len)
              except:
                  print('ARIMA error, skipping to next MA type')
                  continue
              Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
              final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
              mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
              rmse_ftr = mse_ftr ** 0.5
              mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
              mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

              final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
              mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
              rmse = mse ** 0.5
              mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              # Generate prediction accuracy
              actual = df['close'].tail(test_len).values
              result_1 = []
              result_2 = []
              for i in range(1, len(final_prediction)):
                  # Compare prediction to previous close price
                  if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                      result_1.append(1)
                  elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                      result_1.append(1)
                  else:
                      result_1.append(0)

                  # Compare prediction to previous prediction
                  if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                      result_2.append(1)
                  elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                      result_2.append(1)
                  else:
                      result_2.append(0)

              accuracy_1 = np.mean(result_1)
              accuracy_2 = np.mean(result_2)

              simulation1[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                            'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                            'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                            'rmse': rmse_ftr, 'mae' : mae_ftr},
                                'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                          'rmse': rmse, 'mae': mae },
                                'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

              # save simulation data here as checkpoint
              with open('simulation1_data.json', 'w') as fp:
                  json.dump(simulation1, fp)

              for ma in simulation1.keys():
                  print('\n' + ma)
                  print('Prediction vs Close:\t\t' + str(round(100*simulation1[ma]['accuracy']['prediction vs close'], 2))
                        + '% Accuracy')
                  print('Prediction vs Prediction:\t' + str(round(100*simulation1[ma]['accuracy']['prediction vs prediction'], 2))
                        + '% Accuracy')
                  print('MSE:\t', simulation1[ma]['final']['mse'],
                        '\nRMSE:\t', simulation1[ma]['final']['rmse'],
                        '\nMAPE:\t', simulation1[ma]['final']['mae'])#,
                        # '\nMAPE:\t', simulation[ma]['final']['mape'])
            # else:
            #   break
            # code you want to evaluate
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.48 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4157.020, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3687.148, Time=0.05 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.23 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3458.651, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3322.133, Time=0.11 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.74 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.77 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3324.133, Time=0.21 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.697 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1657.067
Date:                Sun, 12 Dec 2021   AIC                           3322.133
Time:                        15:35:45   BIC                           3340.897
Sample:                             0   HQIC                          3329.339
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1966      0.003   -387.226      0.000      -1.203      -1.191
ar.L2         -0.8952      0.006   -138.692      0.000      -0.908      -0.883
ar.L3         -0.3968      0.006    -68.284      0.000      -0.408      -0.385
sigma2         3.5858      0.017    214.535      0.000       3.553       3.619
===================================================================================
Ljung-Box (L1) (Q):                  14.47   Jarque-Bera (JB):           2428881.42
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       271.99
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm_48 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_48 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.49136, saving model to LSTM1.h5
48/48 - 2s - loss: 0.2128 - val_loss: 0.4914 - lr: 0.0010 - 2s/epoch - 40ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.49136 to 0.03252, saving model to LSTM1.h5
48/48 - 0s - loss: 0.1132 - val_loss: 0.0325 - lr: 0.0010 - 474ms/epoch - 10ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0752 - val_loss: 0.4517 - lr: 0.0010 - 409ms/epoch - 9ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0775 - val_loss: 0.1138 - lr: 0.0010 - 405ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0807 - val_loss: 0.2971 - lr: 0.0010 - 484ms/epoch - 10ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0607 - val_loss: 0.1280 - lr: 0.0010 - 392ms/epoch - 8ms/step
Epoch 7/500

Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00007: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0445 - val_loss: 0.2664 - lr: 0.0010 - 438ms/epoch - 9ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0460 - val_loss: 0.2209 - lr: 1.0000e-04 - 431ms/epoch - 9ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0442 - val_loss: 0.1911 - lr: 1.0000e-04 - 415ms/epoch - 9ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0429 - val_loss: 0.1582 - lr: 1.0000e-04 - 392ms/epoch - 8ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0394 - val_loss: 0.1458 - lr: 1.0000e-04 - 431ms/epoch - 9ms/step
Epoch 12/500

Epoch 00012: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00012: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0360 - val_loss: 0.1350 - lr: 1.0000e-04 - 444ms/epoch - 9ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0347 - val_loss: 0.1336 - lr: 1.0000e-05 - 426ms/epoch - 9ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0312 - val_loss: 0.1331 - lr: 1.0000e-05 - 482ms/epoch - 10ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0333 - val_loss: 0.1328 - lr: 1.0000e-05 - 390ms/epoch - 8ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0313 - val_loss: 0.1316 - lr: 1.0000e-05 - 419ms/epoch - 9ms/step
Epoch 17/500

Epoch 00017: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00017: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0361 - val_loss: 0.1306 - lr: 1.0000e-05 - 384ms/epoch - 8ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0350 - val_loss: 0.1300 - lr: 1.0000e-05 - 392ms/epoch - 8ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0374 - val_loss: 0.1300 - lr: 1.0000e-05 - 442ms/epoch - 9ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0332 - val_loss: 0.1293 - lr: 1.0000e-05 - 437ms/epoch - 9ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0343 - val_loss: 0.1283 - lr: 1.0000e-05 - 429ms/epoch - 9ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0321 - val_loss: 0.1297 - lr: 1.0000e-05 - 388ms/epoch - 8ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0327 - val_loss: 0.1286 - lr: 1.0000e-05 - 431ms/epoch - 9ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0354 - val_loss: 0.1280 - lr: 1.0000e-05 - 419ms/epoch - 9ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0300 - val_loss: 0.1262 - lr: 1.0000e-05 - 427ms/epoch - 9ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0371 - val_loss: 0.1251 - lr: 1.0000e-05 - 399ms/epoch - 8ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0310 - val_loss: 0.1259 - lr: 1.0000e-05 - 380ms/epoch - 8ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0346 - val_loss: 0.1260 - lr: 1.0000e-05 - 413ms/epoch - 9ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0319 - val_loss: 0.1261 - lr: 1.0000e-05 - 433ms/epoch - 9ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0355 - val_loss: 0.1244 - lr: 1.0000e-05 - 415ms/epoch - 9ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0349 - val_loss: 0.1222 - lr: 1.0000e-05 - 403ms/epoch - 8ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0334 - val_loss: 0.1220 - lr: 1.0000e-05 - 399ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.03252
48/48 - 1s - loss: 0.0329 - val_loss: 0.1206 - lr: 1.0000e-05 - 508ms/epoch - 11ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0303 - val_loss: 0.1205 - lr: 1.0000e-05 - 394ms/epoch - 8ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0347 - val_loss: 0.1183 - lr: 1.0000e-05 - 402ms/epoch - 8ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0317 - val_loss: 0.1193 - lr: 1.0000e-05 - 398ms/epoch - 8ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0334 - val_loss: 0.1187 - lr: 1.0000e-05 - 382ms/epoch - 8ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0332 - val_loss: 0.1186 - lr: 1.0000e-05 - 410ms/epoch - 9ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0330 - val_loss: 0.1176 - lr: 1.0000e-05 - 420ms/epoch - 9ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0339 - val_loss: 0.1172 - lr: 1.0000e-05 - 452ms/epoch - 9ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0320 - val_loss: 0.1174 - lr: 1.0000e-05 - 446ms/epoch - 9ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0300 - val_loss: 0.1173 - lr: 1.0000e-05 - 383ms/epoch - 8ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0358 - val_loss: 0.1162 - lr: 1.0000e-05 - 429ms/epoch - 9ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0315 - val_loss: 0.1137 - lr: 1.0000e-05 - 443ms/epoch - 9ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.03252
48/48 - 1s - loss: 0.0318 - val_loss: 0.1128 - lr: 1.0000e-05 - 508ms/epoch - 11ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0355 - val_loss: 0.1126 - lr: 1.0000e-05 - 413ms/epoch - 9ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0350 - val_loss: 0.1122 - lr: 1.0000e-05 - 426ms/epoch - 9ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0328 - val_loss: 0.1127 - lr: 1.0000e-05 - 469ms/epoch - 10ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0336 - val_loss: 0.1123 - lr: 1.0000e-05 - 398ms/epoch - 8ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0347 - val_loss: 0.1106 - lr: 1.0000e-05 - 447ms/epoch - 9ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0322 - val_loss: 0.1083 - lr: 1.0000e-05 - 467ms/epoch - 10ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.03252
48/48 - 0s - loss: 0.0330 - val_loss: 0.1067 - lr: 1.0000e-05 - 418ms/epoch - 9ms/step
Epoch 00052: early stopping

SMA
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 29.509403666146007 
RMSE:	 5.432255854260365 
MAPE:	 4.5288133477558885
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.43 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4231.556, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3761.238, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.27 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3532.227, Time=0.08 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3394.496, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.88 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.64 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3396.496, Time=0.21 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.681 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1693.248
Date:                Sun, 12 Dec 2021   AIC                           3394.496
Time:                        15:37:18   BIC                           3413.260
Sample:                             0   HQIC                          3401.702
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.569      0.000      -1.204      -1.192
ar.L2         -0.8976      0.006   -139.811      0.000      -0.910      -0.885
ar.L3         -0.3984      0.006    -68.662      0.000      -0.410      -0.387
sigma2         3.9230      0.018    215.372      0.000       3.887       3.959
===================================================================================
Ljung-Box (L1) (Q):                  14.54   Jarque-Bera (JB):           2462173.05
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.82
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm_49 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_49 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 1.23130, saving model to LSTM1.h5
16/16 - 2s - loss: 0.1617 - val_loss: 1.2313 - lr: 0.0010 - 2s/epoch - 99ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 1.23130 to 0.03856, saving model to LSTM1.h5
16/16 - 0s - loss: 0.0921 - val_loss: 0.0386 - lr: 0.0010 - 176ms/epoch - 11ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.3979 - val_loss: 0.0917 - lr: 0.0010 - 160ms/epoch - 10ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.1546 - val_loss: 0.1976 - lr: 0.0010 - 147ms/epoch - 9ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0758 - val_loss: 0.1013 - lr: 0.0010 - 143ms/epoch - 9ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0642 - val_loss: 0.0943 - lr: 0.0010 - 158ms/epoch - 10ms/step
Epoch 7/500

Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00007: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0524 - val_loss: 0.0848 - lr: 0.0010 - 162ms/epoch - 10ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0504 - val_loss: 0.0865 - lr: 1.0000e-04 - 140ms/epoch - 9ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0511 - val_loss: 0.0918 - lr: 1.0000e-04 - 153ms/epoch - 10ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0502 - val_loss: 0.0940 - lr: 1.0000e-04 - 154ms/epoch - 10ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0514 - val_loss: 0.0925 - lr: 1.0000e-04 - 152ms/epoch - 10ms/step
Epoch 12/500

Epoch 00012: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00012: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0457 - val_loss: 0.0894 - lr: 1.0000e-04 - 174ms/epoch - 11ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0462 - val_loss: 0.0897 - lr: 1.0000e-05 - 159ms/epoch - 10ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0380 - val_loss: 0.0898 - lr: 1.0000e-05 - 178ms/epoch - 11ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0469 - val_loss: 0.0898 - lr: 1.0000e-05 - 145ms/epoch - 9ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0442 - val_loss: 0.0898 - lr: 1.0000e-05 - 146ms/epoch - 9ms/step
Epoch 17/500

Epoch 00017: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00017: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0457 - val_loss: 0.0899 - lr: 1.0000e-05 - 149ms/epoch - 9ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0446 - val_loss: 0.0899 - lr: 1.0000e-05 - 158ms/epoch - 10ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0461 - val_loss: 0.0897 - lr: 1.0000e-05 - 187ms/epoch - 12ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0463 - val_loss: 0.0893 - lr: 1.0000e-05 - 156ms/epoch - 10ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0468 - val_loss: 0.0888 - lr: 1.0000e-05 - 180ms/epoch - 11ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0439 - val_loss: 0.0886 - lr: 1.0000e-05 - 151ms/epoch - 9ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0480 - val_loss: 0.0884 - lr: 1.0000e-05 - 161ms/epoch - 10ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0425 - val_loss: 0.0883 - lr: 1.0000e-05 - 162ms/epoch - 10ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0418 - val_loss: 0.0886 - lr: 1.0000e-05 - 168ms/epoch - 10ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0400 - val_loss: 0.0886 - lr: 1.0000e-05 - 150ms/epoch - 9ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0462 - val_loss: 0.0887 - lr: 1.0000e-05 - 162ms/epoch - 10ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0472 - val_loss: 0.0882 - lr: 1.0000e-05 - 173ms/epoch - 11ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0441 - val_loss: 0.0880 - lr: 1.0000e-05 - 145ms/epoch - 9ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0488 - val_loss: 0.0882 - lr: 1.0000e-05 - 171ms/epoch - 11ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0443 - val_loss: 0.0880 - lr: 1.0000e-05 - 178ms/epoch - 11ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0478 - val_loss: 0.0876 - lr: 1.0000e-05 - 143ms/epoch - 9ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0426 - val_loss: 0.0871 - lr: 1.0000e-05 - 161ms/epoch - 10ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0439 - val_loss: 0.0871 - lr: 1.0000e-05 - 148ms/epoch - 9ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0435 - val_loss: 0.0869 - lr: 1.0000e-05 - 162ms/epoch - 10ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0400 - val_loss: 0.0874 - lr: 1.0000e-05 - 152ms/epoch - 9ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0463 - val_loss: 0.0875 - lr: 1.0000e-05 - 165ms/epoch - 10ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0443 - val_loss: 0.0871 - lr: 1.0000e-05 - 147ms/epoch - 9ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0469 - val_loss: 0.0871 - lr: 1.0000e-05 - 144ms/epoch - 9ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0461 - val_loss: 0.0865 - lr: 1.0000e-05 - 143ms/epoch - 9ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0434 - val_loss: 0.0862 - lr: 1.0000e-05 - 142ms/epoch - 9ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0430 - val_loss: 0.0864 - lr: 1.0000e-05 - 153ms/epoch - 10ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0430 - val_loss: 0.0859 - lr: 1.0000e-05 - 156ms/epoch - 10ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0440 - val_loss: 0.0857 - lr: 1.0000e-05 - 164ms/epoch - 10ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0438 - val_loss: 0.0854 - lr: 1.0000e-05 - 140ms/epoch - 9ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0425 - val_loss: 0.0853 - lr: 1.0000e-05 - 142ms/epoch - 9ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0445 - val_loss: 0.0846 - lr: 1.0000e-05 - 154ms/epoch - 10ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0461 - val_loss: 0.0848 - lr: 1.0000e-05 - 155ms/epoch - 10ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0432 - val_loss: 0.0848 - lr: 1.0000e-05 - 153ms/epoch - 10ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0427 - val_loss: 0.0845 - lr: 1.0000e-05 - 157ms/epoch - 10ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0426 - val_loss: 0.0841 - lr: 1.0000e-05 - 179ms/epoch - 11ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.03856
16/16 - 0s - loss: 0.0439 - val_loss: 0.0840 - lr: 1.0000e-05 - 138ms/epoch - 9ms/step
Epoch 00052: early stopping

SMA
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 29.509403666146007 
RMSE:	 5.432255854260365 
MAPE:	 4.5288133477558885

EMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 28.603272766421263 
RMSE:	 5.348202760406646 
MAPE:	 4.3952252144553965
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.42 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4264.089, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3793.930, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.24 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3564.923, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3427.258, Time=0.08 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.29 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.44 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3429.258, Time=0.19 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.809 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1709.629
Date:                Sun, 12 Dec 2021   AIC                           3427.258
Time:                        15:38:38   BIC                           3446.021
Sample:                             0   HQIC                          3434.464
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1981      0.003   -389.386      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.699      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.737      0.000      -0.410      -0.387
sigma2         4.0860      0.019    215.311      0.000       4.049       4.123
===================================================================================
Ljung-Box (L1) (Q):                  14.57   Jarque-Bera (JB):           2460901.70
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.75
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm_50 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_50 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.74867, saving model to LSTM1.h5
17/17 - 2s - loss: 0.4575 - val_loss: 0.7487 - lr: 0.0010 - 2s/epoch - 93ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.74867 to 0.25174, saving model to LSTM1.h5
17/17 - 0s - loss: 0.1118 - val_loss: 0.2517 - lr: 0.0010 - 195ms/epoch - 11ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.25174 to 0.15433, saving model to LSTM1.h5
17/17 - 0s - loss: 0.1083 - val_loss: 0.1543 - lr: 0.0010 - 172ms/epoch - 10ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.15433
17/17 - 0s - loss: 0.1324 - val_loss: 0.1817 - lr: 0.0010 - 162ms/epoch - 10ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.15433 to 0.09425, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0746 - val_loss: 0.0942 - lr: 0.0010 - 174ms/epoch - 10ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.09425 to 0.06911, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0537 - val_loss: 0.0691 - lr: 0.0010 - 177ms/epoch - 10ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.06911
17/17 - 0s - loss: 0.0534 - val_loss: 0.0721 - lr: 0.0010 - 163ms/epoch - 10ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.06911 to 0.05185, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0602 - val_loss: 0.0519 - lr: 0.0010 - 204ms/epoch - 12ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.05185
17/17 - 0s - loss: 0.0471 - val_loss: 0.0846 - lr: 0.0010 - 164ms/epoch - 10ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.05185
17/17 - 0s - loss: 0.0429 - val_loss: 0.0621 - lr: 0.0010 - 160ms/epoch - 9ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.05185 to 0.05073, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0459 - val_loss: 0.0507 - lr: 0.0010 - 161ms/epoch - 9ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.05073 to 0.04830, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0351 - val_loss: 0.0483 - lr: 0.0010 - 166ms/epoch - 10ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04830
17/17 - 0s - loss: 0.0385 - val_loss: 0.0662 - lr: 0.0010 - 166ms/epoch - 10ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04830
17/17 - 0s - loss: 0.0319 - val_loss: 0.0607 - lr: 0.0010 - 163ms/epoch - 10ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04830
17/17 - 0s - loss: 0.0315 - val_loss: 0.0621 - lr: 0.0010 - 167ms/epoch - 10ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.04830
17/17 - 0s - loss: 0.0306 - val_loss: 0.0662 - lr: 0.0010 - 153ms/epoch - 9ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.04830 to 0.04409, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0321 - val_loss: 0.0441 - lr: 0.0010 - 167ms/epoch - 10ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04409
17/17 - 0s - loss: 0.0254 - val_loss: 0.0749 - lr: 0.0010 - 156ms/epoch - 9ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04409
17/17 - 0s - loss: 0.0323 - val_loss: 0.0527 - lr: 0.0010 - 162ms/epoch - 10ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04409
17/17 - 0s - loss: 0.0318 - val_loss: 0.0809 - lr: 0.0010 - 160ms/epoch - 9ms/step
Epoch 21/500

Epoch 00021: val_loss improved from 0.04409 to 0.03896, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0275 - val_loss: 0.0390 - lr: 0.0010 - 227ms/epoch - 13ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.03896
17/17 - 0s - loss: 0.0314 - val_loss: 0.0715 - lr: 0.0010 - 152ms/epoch - 9ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.03896
17/17 - 0s - loss: 0.0339 - val_loss: 0.0443 - lr: 0.0010 - 148ms/epoch - 9ms/step
Epoch 24/500

Epoch 00024: val_loss improved from 0.03896 to 0.02617, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0369 - val_loss: 0.0262 - lr: 0.0010 - 178ms/epoch - 10ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.02617
17/17 - 0s - loss: 0.0455 - val_loss: 0.0532 - lr: 0.0010 - 166ms/epoch - 10ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.02617
17/17 - 0s - loss: 0.0427 - val_loss: 0.0415 - lr: 0.0010 - 167ms/epoch - 10ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.02617
17/17 - 0s - loss: 0.0466 - val_loss: 0.0819 - lr: 0.0010 - 153ms/epoch - 9ms/step
Epoch 28/500

Epoch 00028: val_loss improved from 0.02617 to 0.02424, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0300 - val_loss: 0.0242 - lr: 0.0010 - 180ms/epoch - 11ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.02424
17/17 - 0s - loss: 0.0331 - val_loss: 0.0634 - lr: 0.0010 - 173ms/epoch - 10ms/step
Epoch 30/500

Epoch 00030: val_loss improved from 0.02424 to 0.02407, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0271 - val_loss: 0.0241 - lr: 0.0010 - 173ms/epoch - 10ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.02407
17/17 - 0s - loss: 0.0243 - val_loss: 0.0297 - lr: 0.0010 - 186ms/epoch - 11ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.02407
17/17 - 0s - loss: 0.0235 - val_loss: 0.0328 - lr: 0.0010 - 150ms/epoch - 9ms/step
Epoch 33/500

Epoch 00033: val_loss improved from 0.02407 to 0.02338, saving model to LSTM1.h5
17/17 - 0s - loss: 0.0233 - val_loss: 0.0234 - lr: 0.0010 - 171ms/epoch - 10ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0260 - val_loss: 0.0238 - lr: 0.0010 - 155ms/epoch - 9ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0222 - val_loss: 0.1222 - lr: 0.0010 - 163ms/epoch - 10ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0231 - val_loss: 0.0304 - lr: 0.0010 - 154ms/epoch - 9ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0271 - val_loss: 0.0643 - lr: 0.0010 - 222ms/epoch - 13ms/step
Epoch 38/500

Epoch 00038: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00038: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0225 - val_loss: 0.0321 - lr: 0.0010 - 179ms/epoch - 11ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0224 - val_loss: 0.0361 - lr: 1.0000e-04 - 163ms/epoch - 10ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0231 - val_loss: 0.0362 - lr: 1.0000e-04 - 156ms/epoch - 9ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0217 - val_loss: 0.0379 - lr: 1.0000e-04 - 148ms/epoch - 9ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0202 - val_loss: 0.0373 - lr: 1.0000e-04 - 155ms/epoch - 9ms/step
Epoch 43/500

Epoch 00043: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00043: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0205 - val_loss: 0.0361 - lr: 1.0000e-04 - 158ms/epoch - 9ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0211 - val_loss: 0.0360 - lr: 1.0000e-05 - 165ms/epoch - 10ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0207 - val_loss: 0.0358 - lr: 1.0000e-05 - 160ms/epoch - 9ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0193 - val_loss: 0.0357 - lr: 1.0000e-05 - 155ms/epoch - 9ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0204 - val_loss: 0.0357 - lr: 1.0000e-05 - 150ms/epoch - 9ms/step
Epoch 48/500

Epoch 00048: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00048: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0213 - val_loss: 0.0358 - lr: 1.0000e-05 - 155ms/epoch - 9ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0206 - val_loss: 0.0359 - lr: 1.0000e-05 - 166ms/epoch - 10ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0212 - val_loss: 0.0359 - lr: 1.0000e-05 - 159ms/epoch - 9ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0217 - val_loss: 0.0361 - lr: 1.0000e-05 - 166ms/epoch - 10ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0217 - val_loss: 0.0363 - lr: 1.0000e-05 - 176ms/epoch - 10ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0212 - val_loss: 0.0363 - lr: 1.0000e-05 - 190ms/epoch - 11ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0202 - val_loss: 0.0363 - lr: 1.0000e-05 - 161ms/epoch - 9ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0203 - val_loss: 0.0362 - lr: 1.0000e-05 - 158ms/epoch - 9ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0202 - val_loss: 0.0361 - lr: 1.0000e-05 - 170ms/epoch - 10ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0225 - val_loss: 0.0360 - lr: 1.0000e-05 - 158ms/epoch - 9ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0206 - val_loss: 0.0360 - lr: 1.0000e-05 - 163ms/epoch - 10ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0213 - val_loss: 0.0359 - lr: 1.0000e-05 - 152ms/epoch - 9ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0200 - val_loss: 0.0360 - lr: 1.0000e-05 - 159ms/epoch - 9ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0187 - val_loss: 0.0359 - lr: 1.0000e-05 - 151ms/epoch - 9ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0204 - val_loss: 0.0359 - lr: 1.0000e-05 - 170ms/epoch - 10ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0210 - val_loss: 0.0360 - lr: 1.0000e-05 - 183ms/epoch - 11ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0201 - val_loss: 0.0362 - lr: 1.0000e-05 - 180ms/epoch - 11ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0198 - val_loss: 0.0365 - lr: 1.0000e-05 - 189ms/epoch - 11ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0218 - val_loss: 0.0369 - lr: 1.0000e-05 - 161ms/epoch - 9ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0209 - val_loss: 0.0367 - lr: 1.0000e-05 - 170ms/epoch - 10ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0213 - val_loss: 0.0369 - lr: 1.0000e-05 - 164ms/epoch - 10ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0215 - val_loss: 0.0369 - lr: 1.0000e-05 - 170ms/epoch - 10ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0207 - val_loss: 0.0371 - lr: 1.0000e-05 - 154ms/epoch - 9ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0203 - val_loss: 0.0371 - lr: 1.0000e-05 - 148ms/epoch - 9ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0213 - val_loss: 0.0371 - lr: 1.0000e-05 - 150ms/epoch - 9ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0207 - val_loss: 0.0370 - lr: 1.0000e-05 - 156ms/epoch - 9ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0231 - val_loss: 0.0371 - lr: 1.0000e-05 - 173ms/epoch - 10ms/step
Epoch 75/500

Epoch 00075: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0232 - val_loss: 0.0368 - lr: 1.0000e-05 - 158ms/epoch - 9ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0205 - val_loss: 0.0367 - lr: 1.0000e-05 - 161ms/epoch - 9ms/step
Epoch 77/500

Epoch 00077: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0197 - val_loss: 0.0365 - lr: 1.0000e-05 - 167ms/epoch - 10ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0203 - val_loss: 0.0364 - lr: 1.0000e-05 - 149ms/epoch - 9ms/step
Epoch 79/500

Epoch 00079: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0211 - val_loss: 0.0365 - lr: 1.0000e-05 - 152ms/epoch - 9ms/step
Epoch 80/500

Epoch 00080: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0221 - val_loss: 0.0365 - lr: 1.0000e-05 - 174ms/epoch - 10ms/step
Epoch 81/500

Epoch 00081: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0195 - val_loss: 0.0367 - lr: 1.0000e-05 - 157ms/epoch - 9ms/step
Epoch 82/500

Epoch 00082: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0189 - val_loss: 0.0368 - lr: 1.0000e-05 - 161ms/epoch - 9ms/step
Epoch 83/500

Epoch 00083: val_loss did not improve from 0.02338
17/17 - 0s - loss: 0.0204 - val_loss: 0.0367 - lr: 1.0000e-05 - 157ms/epoch - 9ms/step
Epoch 00083: early stopping

SMA
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 29.509403666146007 
RMSE:	 5.432255854260365 
MAPE:	 4.5288133477558885

EMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	50.37% Accuracy
MSE:	 28.603272766421263 
RMSE:	 5.348202760406646 
MAPE:	 4.3952252144553965

WMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	46.64% Accuracy
MSE:	 80.72598349686672 
RMSE:	 8.9847639644493 
MAPE:	 7.266216353433966
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.42 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4436.126, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3965.317, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.37 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3736.589, Time=0.08 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3598.951, Time=0.08 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.94 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.89 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3600.951, Time=0.21 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.051 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1795.475
Date:                Sun, 12 Dec 2021   AIC                           3598.951
Time:                        15:40:07   BIC                           3617.714
Sample:                             0   HQIC                          3606.157
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1983      0.003   -389.581      0.000      -1.204      -1.192
ar.L2         -0.8973      0.006   -139.732      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.649      0.000      -0.410      -0.387
sigma2         5.0573      0.023    215.292      0.000       5.011       5.103
===================================================================================
Ljung-Box (L1) (Q):                  14.41   Jarque-Bera (JB):           2460553.80
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.89
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.74
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

WARNING:tensorflow:Layer lstm_51 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Architecture used¶

from google.colab import files
import cv2
uploaded = files.upload()

img = cv2.imread('Experiment1.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)

<matplotlib.image.AxesImage at 0x7fa5ea520ad0>

https://github.com/RalucaChis/Analysis-and-Prediction-of-Stock-Market-Values/blob/d93b921e491dd137b9c3b4642c58506820148d8c/algorithms/ARIMA.py

https://newbedev.com/how-to-install-ta-lib-in-google-colab

Excess kurtosis is a metric that compares the kurtosis of a distribution against the kurtosis of a normal distribution. The kurtosis of a normal distribution equals 3. Therefore, the excess kurtosis is found using the formula below:

Excess Kurtosis = Kurtosis – 3

Model Plots¶

np.save("X_train_appl.npy", X_train)
np.save("y_train_appl.npy", y_train)
np.save("X_test_appl.npy", X_test)
np.save("y_test_appl.npy", y_test)
np.save("yc_train_appl.npy", yc_train)
np.save("yc_test_appl.npy", yc_test)
np.save('index_train_appl.npy', index_train)
np.save('index_test_appl.npy', index_test)

list(simulation1.keys())

['SMA', 'EMA', 'WMA', 'DEMA', 'KAMA', 'MIDPOINT', 'T3', 'TEMA']

for i in range(len(list(simulation1.keys()))):
  SIM = list(simulation1.keys())[i]
  plot_train(simulation1,SIM)
  plot_test(simulation1,SIM)

----- Train RMSE for SMA ----- 7.895573621826288
----- Train_MSE_LSTM for SMA ----- 62.34008281767908
----- Train MAE LSTM for SMA ----- 6.764936516294256

----- Test RMSE for SMA----- 5.432255854260365
----- Test_MSE_LSTM for SMA----- 29.509403666146007
----- Test_MAE_LSTM for SMA----- 4.5288133477558885

----- Train RMSE for EMA ----- 8.87769382903084
----- Train_MSE_LSTM for EMA ----- 78.81344772201226
----- Train MAE LSTM for EMA ----- 7.790667497096491

----- Test RMSE for EMA----- 5.348202760406646
----- Test_MSE_LSTM for EMA----- 28.603272766421263
----- Test_MAE_LSTM for EMA----- 4.3952252144553965

----- Train RMSE for WMA ----- 9.703993025462333
----- Train_MSE_LSTM for WMA ----- 94.16748063822159
----- Train MAE LSTM for WMA ----- 8.628062737580057

----- Test RMSE for WMA----- 8.9847639644493
----- Test_MSE_LSTM for WMA----- 80.72598349686672
----- Test_MAE_LSTM for WMA----- 7.266216353433966

----- Train RMSE for DEMA ----- 11.240117396029953
----- Train_MSE_LSTM for DEMA ----- 126.3402390765352
----- Train MAE LSTM for DEMA ----- 10.016611697382782

----- Test RMSE for DEMA----- 8.654168316183721
----- Test_MSE_LSTM for DEMA----- 74.8946292448382
----- Test_MAE_LSTM for DEMA----- 7.175854729849037

----- Train RMSE for KAMA ----- 9.358621140016876
----- Train_MSE_LSTM for KAMA ----- 87.58378964237077
----- Train MAE LSTM for KAMA ----- 8.463473867850913

----- Test RMSE for KAMA----- 4.87546037487117
----- Test_MSE_LSTM for KAMA----- 23.77011386693893
----- Test_MAE_LSTM for KAMA----- 3.900500517739451

Univariate Arima Multistep MutiVariate LSTM Hybrid Model Experiment 2¶

def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det = 20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # # Option 1
    # # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    # model.add(Dense(units=64,activation='relu'))
    # model.add(Dropout(0.5))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    # ## Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()


    # option 2
    model = Sequential()
    model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    model.add(Dense(64))
    model.add(Dense(units=output_dim))
    model.compile(optimizer=Adam(learning_rate = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM2.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()




    # Option 3
    # define custom activation
    # reference: https://github.com/Vaibhav-Sachdeva/Correlation-Coefficient-Prediction-using-ARIMA-LSTM-Hybrid-Model/blob/main/Code/LSTM-ARIMA.ipynb
    # class Double_Tanh(Activation):
    #     def __init__(self, activation, **kwargs):
    #         super(Double_Tanh, self).__init__(activation, **kwargs)
    #         self.__name__ = 'double_tanh'

    # def double_tanh(x):
    #     return (K.tanh(x) * 2)

    # get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
    #     # Model Generation
    # model = Sequential()
    # #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    # model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    # model.add(Dense(1))
    # model.add(Activation(double_tanh))
    # model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(x_train.shape[1], 1)))
    # model.add(LSTM(units=int(lstm_len/2)))
    # model.add(Dense(1, activation='sigmoid'))
    # model.compile(loss='mean_squared_error', optimizer='adam')
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te

if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation2 = {}
    imgfile = 'Experiment2'
    for ma in optimized_period:
              print(ma)
              print(functions[ma])
              print ( int( optimized_period[ma]))
            # if ma == 'SMA':
              low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
              low_vol = low_vol.fillna(0)
              low_vol_data = df['close']
              high_vol = pd.DataFrame()
              df2 = df.copy()
              for i in df2.columns:
                if i in low_vol.columns:
                  high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
              high_vol_data = df['close']
              ## *****************************************************
              # Generate ARIMA and LSTM predictions
              print('\nWorking on ' + ma + ' predictions')
              try:
                print('parameters used : ', train_len, test_len)
                low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima(low_vol,low_vol_data, train_len, test_len)
              except:
                  print('ARIMA error, skipping to next MA type')
                  continue
              Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
              final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
              mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
              rmse_ftr = mse_ftr ** 0.5
              mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
              mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

              final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
              mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
              rmse = mse ** 0.5
              mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              # Generate prediction accuracy
              actual = df['close'].tail(test_len).values
              result_1 = []
              result_2 = []
              for i in range(1, len(final_prediction)):
                  # Compare prediction to previous close price
                  if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                      result_1.append(1)
                  elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                      result_1.append(1)
                  else:
                      result_1.append(0)

                  # Compare prediction to previous prediction
                  if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                      result_2.append(1)
                  elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                      result_2.append(1)
                  else:
                      result_2.append(0)

              accuracy_1 = np.mean(result_1)
              accuracy_2 = np.mean(result_2)

              simulation2[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                            'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                            'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                            'rmse': rmse_ftr, 'mae' : mae_ftr},
                                'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                          'rmse': rmse, 'mae': mae },
                                'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

              # save simulation data here as checkpoint
              with open('simulation2_data.json', 'w') as fp:
                  json.dump(simulation2, fp)

              for ma in simulation2.keys():
                  print('\n' + ma)
                  print('Prediction vs Close:\t\t' + str(round(100*simulation2[ma]['accuracy']['prediction vs close'], 2))
                        + '% Accuracy')
                  print('Prediction vs Prediction:\t' + str(round(100*simulation2[ma]['accuracy']['prediction vs prediction'], 2))
                        + '% Accuracy')
                  print('MSE:\t', simulation2[ma]['final']['mse'],
                        '\nRMSE:\t', simulation2[ma]['final']['rmse'],
                        '\nMAPE:\t', simulation2[ma]['final']['mae'])#,
                        # '\nMAPE:\t', simulation[ma]['final']['mape'])
            # else:
            #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.49 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4157.020, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3687.148, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.20 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3458.651, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3322.133, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.78 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.78 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3324.133, Time=0.23 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.721 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1657.067
Date:                Sun, 12 Dec 2021   AIC                           3322.133
Time:                        14:39:19   BIC                           3340.897
Sample:                             0   HQIC                          3329.339
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1966      0.003   -387.226      0.000      -1.203      -1.191
ar.L2         -0.8952      0.006   -138.692      0.000      -0.908      -0.883
ar.L3         -0.3968      0.006    -68.284      0.000      -0.408      -0.385
sigma2         3.5858      0.017    214.535      0.000       3.553       3.619
===================================================================================
Ljung-Box (L1) (Q):                  14.47   Jarque-Bera (JB):           2428881.42
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       271.99
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.07969, saving model to LSTM2.h5
48/48 - 5s - loss: 0.1695 - accuracy: 0.0000e+00 - val_loss: 0.0797 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 5s/epoch - 107ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.07969 to 0.01348, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0739 - accuracy: 0.0000e+00 - val_loss: 0.0135 - val_accuracy: 0.0037 - lr: 0.0010 - 277ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.01348
48/48 - 0s - loss: 0.0279 - accuracy: 0.0000e+00 - val_loss: 0.0797 - val_accuracy: 0.0037 - lr: 0.0010 - 275ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.01348
48/48 - 0s - loss: 0.0309 - accuracy: 0.0000e+00 - val_loss: 0.0415 - val_accuracy: 0.0037 - lr: 0.0010 - 264ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.01348
48/48 - 0s - loss: 0.0315 - accuracy: 0.0000e+00 - val_loss: 0.0942 - val_accuracy: 0.0037 - lr: 0.0010 - 302ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.01348
48/48 - 0s - loss: 0.0188 - accuracy: 0.0000e+00 - val_loss: 0.0229 - val_accuracy: 0.0037 - lr: 0.0010 - 247ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00007: val_loss did not improve from 0.01348
48/48 - 0s - loss: 0.0113 - accuracy: 0.0000e+00 - val_loss: 0.0192 - val_accuracy: 0.0037 - lr: 0.0010 - 270ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.01348 to 0.00813, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0084 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 307ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.00813 to 0.00673, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0021 - accuracy: 0.0000e+00 - val_loss: 0.0067 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 299ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.00673 to 0.00586, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0019 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 263ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.00586 to 0.00530, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 307ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.00530 to 0.00495, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 287ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.00495 to 0.00474, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 268ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.00474 to 0.00460, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 290ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss improved from 0.00460 to 0.00452, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 302ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: val_loss improved from 0.00452 to 0.00446, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 297ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.00446 to 0.00442, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 263ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss improved from 0.00442 to 0.00440, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 304ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss improved from 0.00440 to 0.00438, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 295ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.00438 to 0.00438, saving model to LSTM2.h5
48/48 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 310ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00021: val_loss did not improve from 0.00438
48/48 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 294ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.5672e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 270ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.5419e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 255ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.5241e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 255ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.5093e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 272ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00026: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.4956e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 259ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.4821e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 264ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.4686e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 269ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.4549e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 291ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.4411e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 266ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.4272e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 282ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.4131e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 266ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.3989e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.3845e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 258ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.3700e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 279ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.3554e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 267ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.3407e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.3259e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 267ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.3110e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 284ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.2961e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 268ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.2810e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 264ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.2659e-04 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 260ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.2506e-04 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 270ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.2353e-04 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 292ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.2200e-04 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 247ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.2045e-04 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 260ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.1890e-04 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 275ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.1735e-04 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 258ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.1578e-04 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 252ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.1421e-04 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 257ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.1264e-04 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 274ms/epoch - 6ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.1105e-04 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 258ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.0947e-04 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 256ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.0787e-04 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 268ms/epoch - 6ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.0627e-04 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 302ms/epoch - 6ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.0466e-04 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.0305e-04 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00438
48/48 - 0s - loss: 9.0143e-04 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 275ms/epoch - 6ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00438
48/48 - 0s - loss: 8.9980e-04 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 279ms/epoch - 6ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00438
48/48 - 0s - loss: 8.9817e-04 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 276ms/epoch - 6ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.00438
48/48 - 0s - loss: 8.9653e-04 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 278ms/epoch - 6ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.00438
48/48 - 0s - loss: 8.9488e-04 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 309ms/epoch - 6ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.00438
48/48 - 0s - loss: 8.9323e-04 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 252ms/epoch - 5ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.00438
48/48 - 0s - loss: 8.9156e-04 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 293ms/epoch - 6ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.00438
48/48 - 0s - loss: 8.8989e-04 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 293ms/epoch - 6ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.00438
48/48 - 0s - loss: 8.8821e-04 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 268ms/epoch - 6ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.00438
48/48 - 0s - loss: 8.8652e-04 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 251ms/epoch - 5ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.00438
48/48 - 0s - loss: 8.8483e-04 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 276ms/epoch - 6ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.00438
48/48 - 0s - loss: 8.8312e-04 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 276ms/epoch - 6ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.00438
48/48 - 0s - loss: 8.8141e-04 - accuracy: 0.0000e+00 - val_loss: 0.0050 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 281ms/epoch - 6ms/step
Epoch 00070: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 75.20110458138421 
RMSE:	 8.67185704341257 
MAPE:	 7.0799160587584336
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.40 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4231.556, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3761.238, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.30 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3532.227, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3394.496, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.84 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.62 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3396.496, Time=0.20 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.590 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1693.248
Date:                Sun, 12 Dec 2021   AIC                           3394.496
Time:                        14:41:12   BIC                           3413.260
Sample:                             0   HQIC                          3401.702
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.569      0.000      -1.204      -1.192
ar.L2         -0.8976      0.006   -139.811      0.000      -0.910      -0.885
ar.L3         -0.3984      0.006    -68.662      0.000      -0.410      -0.387
sigma2         3.9230      0.018    215.372      0.000       3.887       3.959
===================================================================================
Ljung-Box (L1) (Q):                  14.54   Jarque-Bera (JB):           2462173.05
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.82
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.11100, saving model to LSTM2.h5
16/16 - 3s - loss: 0.1653 - accuracy: 0.0000e+00 - val_loss: 0.1110 - val_accuracy: 0.0037 - lr: 0.0010 - 3s/epoch - 214ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.11100 to 0.06946, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0510 - accuracy: 0.0000e+00 - val_loss: 0.0695 - val_accuracy: 0.0037 - lr: 0.0010 - 115ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.06946 to 0.00950, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0063 - accuracy: 0.0000e+00 - val_loss: 0.0095 - val_accuracy: 0.0037 - lr: 0.0010 - 128ms/epoch - 8ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.00950 to 0.00842, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0035 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 0.0010 - 118ms/epoch - 7ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.00842 to 0.00799, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0067 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 0.0010 - 119ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00799
16/16 - 0s - loss: 0.0025 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 0.0010 - 106ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00799
16/16 - 0s - loss: 0.0031 - accuracy: 0.0000e+00 - val_loss: 0.0148 - val_accuracy: 0.0037 - lr: 0.0010 - 102ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00799
16/16 - 0s - loss: 0.0063 - accuracy: 0.0000e+00 - val_loss: 0.0208 - val_accuracy: 0.0037 - lr: 0.0010 - 103ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00799
16/16 - 0s - loss: 0.0062 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 0.0010 - 104ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00010: val_loss did not improve from 0.00799
16/16 - 0s - loss: 0.0109 - accuracy: 0.0000e+00 - val_loss: 0.0122 - val_accuracy: 0.0037 - lr: 0.0010 - 107ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.00799 to 0.00723, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0160 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 125ms/epoch - 8ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.00723 to 0.00560, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0062 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 124ms/epoch - 8ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.00560 to 0.00528, saving model to LSTM2.h5
16/16 - 0s - loss: 0.0038 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 116ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0035 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 121ms/epoch - 8ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0027 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 114ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0023 - accuracy: 0.0000e+00 - val_loss: 0.0062 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 97ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0020 - accuracy: 0.0000e+00 - val_loss: 0.0064 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 100ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00018: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 96ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 23/500

Epoch 00023: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00023: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 119ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.00528
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 00063: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 75.20110458138421 
RMSE:	 8.67185704341257 
MAPE:	 7.0799160587584336

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 61.82384712230415 
RMSE:	 7.862814198638052 
MAPE:	 6.504666247736678
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.40 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4264.089, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3793.930, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.23 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3564.923, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3427.258, Time=0.08 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.20 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.45 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3429.258, Time=0.18 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.686 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1709.629
Date:                Sun, 12 Dec 2021   AIC                           3427.258
Time:                        14:42:30   BIC                           3446.021
Sample:                             0   HQIC                          3434.464
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1981      0.003   -389.386      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.699      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.737      0.000      -0.410      -0.387
sigma2         4.0860      0.019    215.311      0.000       4.049       4.123
===================================================================================
Ljung-Box (L1) (Q):                  14.57   Jarque-Bera (JB):           2460901.70
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.75
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.20292, saving model to LSTM2.h5
17/17 - 4s - loss: 0.1103 - accuracy: 0.0000e+00 - val_loss: 0.2029 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 4s/epoch - 210ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.20292 to 0.11069, saving model to LSTM2.h5
17/17 - 0s - loss: 0.1639 - accuracy: 0.0000e+00 - val_loss: 0.1107 - val_accuracy: 0.0037 - lr: 0.0010 - 119ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.11069 to 0.05673, saving model to LSTM2.h5
17/17 - 0s - loss: 0.1197 - accuracy: 0.0000e+00 - val_loss: 0.0567 - val_accuracy: 0.0037 - lr: 0.0010 - 129ms/epoch - 8ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.05673
17/17 - 0s - loss: 0.0248 - accuracy: 0.0000e+00 - val_loss: 0.0785 - val_accuracy: 0.0037 - lr: 0.0010 - 110ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.05673 to 0.00858, saving model to LSTM2.h5
17/17 - 0s - loss: 0.0488 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 0.0010 - 128ms/epoch - 8ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00858
17/17 - 0s - loss: 0.0060 - accuracy: 0.0000e+00 - val_loss: 0.0092 - val_accuracy: 0.0037 - lr: 0.0010 - 105ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00858
17/17 - 0s - loss: 0.0107 - accuracy: 0.0000e+00 - val_loss: 0.0110 - val_accuracy: 0.0037 - lr: 0.0010 - 100ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00858
17/17 - 0s - loss: 0.0024 - accuracy: 0.0000e+00 - val_loss: 0.0094 - val_accuracy: 0.0037 - lr: 0.0010 - 116ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.00858 to 0.00558, saving model to LSTM2.h5
17/17 - 0s - loss: 0.0031 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 0.0010 - 143ms/epoch - 8ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00558
17/17 - 0s - loss: 0.0021 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 0.0010 - 108ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00558
17/17 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 0.0010 - 116ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00558
17/17 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 0.0010 - 107ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.00558 to 0.00475, saving model to LSTM2.h5
17/17 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 0.0010 - 135ms/epoch - 8ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00475
17/17 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 0.0010 - 110ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00475
17/17 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 0.0010 - 115ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00475
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 0.0010 - 115ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00475
17/17 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 0.0010 - 111ms/epoch - 7ms/step
Epoch 18/500

Epoch 00018: val_loss improved from 0.00475 to 0.00452, saving model to LSTM2.h5
17/17 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 0.0010 - 130ms/epoch - 8ms/step
Epoch 19/500

Epoch 00019: val_loss improved from 0.00452 to 0.00443, saving model to LSTM2.h5
17/17 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 0.0010 - 142ms/epoch - 8ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00443
17/17 - 0s - loss: 0.0019 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 0.0010 - 94ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00443
17/17 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 0.0010 - 112ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00443
17/17 - 0s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0092 - val_accuracy: 0.0037 - lr: 0.0010 - 110ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00023: val_loss did not improve from 0.00443
17/17 - 0s - loss: 0.0022 - accuracy: 0.0000e+00 - val_loss: 0.0087 - val_accuracy: 0.0037 - lr: 0.0010 - 105ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00443
17/17 - 0s - loss: 0.0024 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 106ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00443
17/17 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 111ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00443
17/17 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 118ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00443
17/17 - 0s - loss: 9.7258e-04 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 107ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00028: val_loss did not improve from 0.00443
17/17 - 0s - loss: 9.1754e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 115ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.8722e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 121ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.8510e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 109ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.8283e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 106ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.8068e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 109ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00033: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.7866e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.7673e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.7488e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 120ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.7309e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 125ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.7134e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.6964e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 108ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.6797e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.6634e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 108ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.6474e-04 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.6318e-04 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.6164e-04 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.6014e-04 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 124ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.5867e-04 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 122ms/epoch - 7ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.5723e-04 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.5582e-04 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.5444e-04 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.5309e-04 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 123ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.5177e-04 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.5048e-04 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 110ms/epoch - 6ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.4922e-04 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 110ms/epoch - 6ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.4798e-04 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.4677e-04 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.4559e-04 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 110ms/epoch - 6ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.4444e-04 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 109ms/epoch - 6ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.4331e-04 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.4221e-04 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 106ms/epoch - 6ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.4113e-04 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 110ms/epoch - 6ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.4007e-04 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 123ms/epoch - 7ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.3904e-04 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 118ms/epoch - 7ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.3803e-04 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.3704e-04 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 120ms/epoch - 7ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.3607e-04 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.3512e-04 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 108ms/epoch - 6ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.3420e-04 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.3329e-04 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.3240e-04 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.00443
17/17 - 0s - loss: 8.3153e-04 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 00069: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 75.20110458138421 
RMSE:	 8.67185704341257 
MAPE:	 7.0799160587584336

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 61.82384712230415 
RMSE:	 7.862814198638052 
MAPE:	 6.504666247736678

WMA
Prediction vs Close:		56.34% Accuracy
Prediction vs Prediction:	45.52% Accuracy
MSE:	 78.06346997131263 
RMSE:	 8.835353415190172 
MAPE:	 6.948265794170055
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.43 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4436.126, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3965.317, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.37 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3736.589, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3598.951, Time=0.08 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.92 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.91 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3600.951, Time=0.18 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.028 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1795.475
Date:                Sun, 12 Dec 2021   AIC                           3598.951
Time:                        14:43:51   BIC                           3617.714
Sample:                             0   HQIC                          3606.157
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1983      0.003   -389.581      0.000      -1.204      -1.192
ar.L2         -0.8973      0.006   -139.732      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.649      0.000      -0.410      -0.387
sigma2         5.0573      0.023    215.292      0.000       5.011       5.103
===================================================================================
Ljung-Box (L1) (Q):                  14.41   Jarque-Bera (JB):           2460553.80
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.89
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.74
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04427, saving model to LSTM2.h5
10/10 - 4s - loss: 0.2331 - accuracy: 0.0000e+00 - val_loss: 0.0443 - val_accuracy: 0.0037 - lr: 0.0010 - 4s/epoch - 388ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.04427 to 0.02873, saving model to LSTM2.h5
10/10 - 0s - loss: 0.1760 - accuracy: 0.0000e+00 - val_loss: 0.0287 - val_accuracy: 0.0037 - lr: 0.0010 - 93ms/epoch - 9ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.02873
10/10 - 0s - loss: 0.0484 - accuracy: 0.0000e+00 - val_loss: 0.0752 - val_accuracy: 0.0037 - lr: 0.0010 - 83ms/epoch - 8ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.02873
10/10 - 0s - loss: 0.0095 - accuracy: 0.0000e+00 - val_loss: 0.0313 - val_accuracy: 0.0037 - lr: 0.0010 - 79ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.02873 to 0.01131, saving model to LSTM2.h5
10/10 - 0s - loss: 0.0045 - accuracy: 0.0000e+00 - val_loss: 0.0113 - val_accuracy: 0.0037 - lr: 0.0010 - 94ms/epoch - 9ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.01131 to 0.01100, saving model to LSTM2.h5
10/10 - 0s - loss: 0.0019 - accuracy: 0.0000e+00 - val_loss: 0.0110 - val_accuracy: 0.0037 - lr: 0.0010 - 95ms/epoch - 10ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0162 - val_accuracy: 0.0037 - lr: 0.0010 - 81ms/epoch - 8ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0209 - val_accuracy: 0.0037 - lr: 0.0010 - 73ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0166 - val_accuracy: 0.0037 - lr: 0.0010 - 75ms/epoch - 7ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0163 - val_accuracy: 0.0037 - lr: 0.0010 - 74ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00011: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0154 - val_accuracy: 0.0037 - lr: 0.0010 - 76ms/epoch - 8ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0157 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 79ms/epoch - 8ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0161 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 96ms/epoch - 10ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0163 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 100ms/epoch - 10ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0165 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 78ms/epoch - 8ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00016: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0166 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 82ms/epoch - 8ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0166 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 84ms/epoch - 8ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0166 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0166 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0166 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00021: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0166 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 84ms/epoch - 8ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0166 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 82ms/epoch - 8ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0166 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0167 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 85ms/epoch - 8ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0167 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 86ms/epoch - 9ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0167 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 89ms/epoch - 9ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0167 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 85ms/epoch - 8ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0167 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0167 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0167 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 91ms/epoch - 9ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0167 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0167 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 82ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0168 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0168 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0168 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0168 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 85ms/epoch - 9ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0168 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0168 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 90ms/epoch - 9ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0168 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 91ms/epoch - 9ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0168 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 82ms/epoch - 8ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0168 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 83ms/epoch - 8ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 79ms/epoch - 8ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 77ms/epoch - 8ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 75ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 80ms/epoch - 8ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 85ms/epoch - 8ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0169 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 101ms/epoch - 10ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0170 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0170 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0170 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0170 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.01100
10/10 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0170 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 88ms/epoch - 9ms/step
Epoch 00056: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 75.20110458138421 
RMSE:	 8.67185704341257 
MAPE:	 7.0799160587584336

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 61.82384712230415 
RMSE:	 7.862814198638052 
MAPE:	 6.504666247736678

WMA
Prediction vs Close:		56.34% Accuracy
Prediction vs Prediction:	45.52% Accuracy
MSE:	 78.06346997131263 
RMSE:	 8.835353415190172 
MAPE:	 6.948265794170055

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 153.59400995187858 
RMSE:	 12.39330504554288 
MAPE:	 11.203775482220726
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.38 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4190.464, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3724.371, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.27 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3494.154, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3357.435, Time=0.10 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.15 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.73 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3359.435, Time=0.22 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.992 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1674.717
Date:                Sun, 12 Dec 2021   AIC                           3357.435
Time:                        14:45:03   BIC                           3376.198
Sample:                             0   HQIC                          3364.641
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1955      0.003   -381.246      0.000      -1.202      -1.189
ar.L2         -0.8964      0.007   -135.835      0.000      -0.909      -0.883
ar.L3         -0.3971      0.006    -67.229      0.000      -0.409      -0.385
sigma2         3.7466      0.018    211.623      0.000       3.712       3.781
===================================================================================
Ljung-Box (L1) (Q):                  14.20   Jarque-Bera (JB):           2338363.32
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             3.76
Prob(H) (two-sided):                  0.00   Kurtosis:                       266.93
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.10383, saving model to LSTM2.h5
45/45 - 4s - loss: 0.1770 - accuracy: 0.0000e+00 - val_loss: 0.1038 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 4s/epoch - 90ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.10383 to 0.01943, saving model to LSTM2.h5
45/45 - 0s - loss: 0.0618 - accuracy: 0.0000e+00 - val_loss: 0.0194 - val_accuracy: 0.0037 - lr: 0.0010 - 266ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.01943
45/45 - 0s - loss: 0.0545 - accuracy: 0.0000e+00 - val_loss: 0.2219 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 286ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.01943
45/45 - 0s - loss: 0.0658 - accuracy: 0.0000e+00 - val_loss: 0.0253 - val_accuracy: 0.0037 - lr: 0.0010 - 240ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.01943
45/45 - 0s - loss: 0.0312 - accuracy: 0.0000e+00 - val_loss: 0.1697 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 274ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.01943
45/45 - 0s - loss: 0.0233 - accuracy: 0.0000e+00 - val_loss: 0.0298 - val_accuracy: 0.0037 - lr: 0.0010 - 258ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.01943 to 0.01815, saving model to LSTM2.h5
45/45 - 0s - loss: 0.0102 - accuracy: 0.0000e+00 - val_loss: 0.0181 - val_accuracy: 0.0037 - lr: 0.0010 - 287ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.01815
45/45 - 0s - loss: 0.0061 - accuracy: 0.0000e+00 - val_loss: 0.0275 - val_accuracy: 0.0037 - lr: 0.0010 - 259ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.01815 to 0.00734, saving model to LSTM2.h5
45/45 - 0s - loss: 0.0049 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 0.0010 - 291ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0027 - accuracy: 0.0000e+00 - val_loss: 0.0410 - val_accuracy: 0.0037 - lr: 0.0010 - 261ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0031 - accuracy: 0.0000e+00 - val_loss: 0.0205 - val_accuracy: 0.0037 - lr: 0.0010 - 295ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0024 - accuracy: 0.0000e+00 - val_loss: 0.0504 - val_accuracy: 0.0037 - lr: 0.0010 - 236ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0031 - accuracy: 0.0000e+00 - val_loss: 0.0254 - val_accuracy: 0.0037 - lr: 0.0010 - 244ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00014: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0024 - accuracy: 0.0000e+00 - val_loss: 0.0518 - val_accuracy: 0.0037 - lr: 0.0010 - 318ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0058 - accuracy: 0.0000e+00 - val_loss: 0.0374 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 270ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0044 - accuracy: 0.0000e+00 - val_loss: 0.0258 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 253ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0028 - accuracy: 0.0000e+00 - val_loss: 0.0207 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 282ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0022 - accuracy: 0.0000e+00 - val_loss: 0.0179 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 285ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00019: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0162 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 278ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0159 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 254ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0156 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 265ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0154 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 254ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0152 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 274ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00024: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0150 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 256ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0149 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 265ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0147 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 273ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0146 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 239ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0145 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 261ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0144 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 265ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0143 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 270ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0141 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 237ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0140 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 264ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0139 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 243ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0138 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 272ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0137 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 263ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0136 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 274ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0135 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 254ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0134 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0133 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 280ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0132 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 257ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0131 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 257ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0130 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 270ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0129 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 253ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0128 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 259ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0127 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 288ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0126 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 245ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0125 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 250ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0124 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 244ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0123 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 249ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0123 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0122 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 253ms/epoch - 6ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0121 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 242ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0120 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0119 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 266ms/epoch - 6ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0118 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 270ms/epoch - 6ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0117 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 249ms/epoch - 6ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0116 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 239ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0116 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 254ms/epoch - 6ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00734
45/45 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0115 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 00059: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 75.20110458138421 
RMSE:	 8.67185704341257 
MAPE:	 7.0799160587584336

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 61.82384712230415 
RMSE:	 7.862814198638052 
MAPE:	 6.504666247736678

WMA
Prediction vs Close:		56.34% Accuracy
Prediction vs Prediction:	45.52% Accuracy
MSE:	 78.06346997131263 
RMSE:	 8.835353415190172 
MAPE:	 6.948265794170055

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 153.59400995187858 
RMSE:	 12.39330504554288 
MAPE:	 11.203775482220726

KAMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 121.28941541171922 
RMSE:	 11.013147388994629 
MAPE:	 9.175643045864026
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14

Working on MIDPOINT predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.35 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4212.289, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3747.746, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.26 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3523.401, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3387.759, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.27 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.85 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3389.758, Time=0.20 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.168 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1689.879
Date:                Sun, 12 Dec 2021   AIC                           3387.759
Time:                        14:46:33   BIC                           3406.522
Sample:                             0   HQIC                          3394.964
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1878      0.003   -345.315      0.000      -1.195      -1.181
ar.L2         -0.8876      0.007   -121.809      0.000      -0.902      -0.873
ar.L3         -0.3957      0.007    -60.127      0.000      -0.409      -0.383
sigma2         3.8904      0.020    193.404      0.000       3.851       3.930
===================================================================================
Ljung-Box (L1) (Q):                  13.21   Jarque-Bera (JB):           1659080.01
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.08   Skew:                             3.28
Prob(H) (two-sided):                  0.00   Kurtosis:                       225.31
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.13473, saving model to LSTM2.h5
58/58 - 4s - loss: 0.1760 - accuracy: 0.0000e+00 - val_loss: 0.1347 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 4s/epoch - 64ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.13473 to 0.00527, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0557 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 0.0010 - 334ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.00527
58/58 - 0s - loss: 0.0038 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 0.0010 - 329ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.00527 to 0.00478, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 0.0010 - 393ms/epoch - 7ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.00478 to 0.00472, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 0.0010 - 375ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0054 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 0.0010 - 333ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0097 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 0.0010 - 307ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0255 - accuracy: 0.0000e+00 - val_loss: 0.0556 - val_accuracy: 0.0037 - lr: 0.0010 - 308ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00009: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0276 - accuracy: 0.0000e+00 - val_loss: 0.0063 - val_accuracy: 0.0037 - lr: 0.0010 - 320ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0433 - accuracy: 0.0000e+00 - val_loss: 0.0879 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 328ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0147 - accuracy: 0.0000e+00 - val_loss: 0.0407 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 308ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0101 - accuracy: 0.0000e+00 - val_loss: 0.0224 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 346ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0081 - accuracy: 0.0000e+00 - val_loss: 0.0130 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 334ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00014: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0066 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 340ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0048 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 328ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0045 - accuracy: 0.0000e+00 - val_loss: 0.0071 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 357ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0043 - accuracy: 0.0000e+00 - val_loss: 0.0067 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 317ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0042 - accuracy: 0.0000e+00 - val_loss: 0.0064 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 338ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00019: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0041 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 306ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0040 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 312ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0039 - accuracy: 0.0000e+00 - val_loss: 0.0057 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 349ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0038 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 330ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0037 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 310ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0036 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 335ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0036 - accuracy: 0.0000e+00 - val_loss: 0.0050 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 310ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0035 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 305ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00472
58/58 - 0s - loss: 0.0034 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 314ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss improved from 0.00472 to 0.00467, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0033 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 348ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss improved from 0.00467 to 0.00457, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0033 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 350ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss improved from 0.00457 to 0.00448, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0032 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 333ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss improved from 0.00448 to 0.00441, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0031 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 345ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss improved from 0.00441 to 0.00435, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0030 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 333ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss improved from 0.00435 to 0.00430, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0030 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 360ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss improved from 0.00430 to 0.00427, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0029 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 396ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss improved from 0.00427 to 0.00425, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0028 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 342ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss improved from 0.00425 to 0.00424, saving model to LSTM2.h5
58/58 - 0s - loss: 0.0027 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 352ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0027 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 309ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0026 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 310ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0025 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 343ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0025 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 311ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0024 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 294ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0023 - accuracy: 0.0000e+00 - val_loss: 0.0045 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 348ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0023 - accuracy: 0.0000e+00 - val_loss: 0.0046 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 318ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0022 - accuracy: 0.0000e+00 - val_loss: 0.0047 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 292ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0022 - accuracy: 0.0000e+00 - val_loss: 0.0048 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 331ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0021 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 308ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0021 - accuracy: 0.0000e+00 - val_loss: 0.0050 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 306ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0020 - accuracy: 0.0000e+00 - val_loss: 0.0052 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 340ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0020 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 313ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0019 - accuracy: 0.0000e+00 - val_loss: 0.0055 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 325ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0019 - accuracy: 0.0000e+00 - val_loss: 0.0056 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 349ms/epoch - 6ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 325ms/epoch - 6ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 321ms/epoch - 6ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 356ms/epoch - 6ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0063 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 328ms/epoch - 6ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 339ms/epoch - 6ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0067 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 342ms/epoch - 6ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0069 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 315ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0071 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 307ms/epoch - 5ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 339ms/epoch - 6ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 325ms/epoch - 6ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 316ms/epoch - 5ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 376ms/epoch - 6ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 356ms/epoch - 6ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 315ms/epoch - 5ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0082 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 339ms/epoch - 6ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 324ms/epoch - 6ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0085 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 303ms/epoch - 5ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 328ms/epoch - 6ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0088 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 342ms/epoch - 6ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0089 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 302ms/epoch - 5ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0090 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 323ms/epoch - 6ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0090 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 318ms/epoch - 5ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0091 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 297ms/epoch - 5ms/step
Epoch 75/500

Epoch 00075: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0092 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 328ms/epoch - 6ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0092 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 322ms/epoch - 6ms/step
Epoch 77/500

Epoch 00077: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0093 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 310ms/epoch - 5ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0093 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 321ms/epoch - 6ms/step
Epoch 79/500

Epoch 00079: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0093 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 304ms/epoch - 5ms/step
Epoch 80/500

Epoch 00080: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0093 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 314ms/epoch - 5ms/step
Epoch 81/500

Epoch 00081: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0093 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 307ms/epoch - 5ms/step
Epoch 82/500

Epoch 00082: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0093 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 325ms/epoch - 6ms/step
Epoch 83/500

Epoch 00083: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0093 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 309ms/epoch - 5ms/step
Epoch 84/500

Epoch 00084: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0092 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 310ms/epoch - 5ms/step
Epoch 85/500

Epoch 00085: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0092 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 388ms/epoch - 7ms/step
Epoch 86/500

Epoch 00086: val_loss did not improve from 0.00424
58/58 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0091 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 327ms/epoch - 6ms/step
Epoch 00086: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 75.20110458138421 
RMSE:	 8.67185704341257 
MAPE:	 7.0799160587584336

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 61.82384712230415 
RMSE:	 7.862814198638052 
MAPE:	 6.504666247736678

WMA
Prediction vs Close:		56.34% Accuracy
Prediction vs Prediction:	45.52% Accuracy
MSE:	 78.06346997131263 
RMSE:	 8.835353415190172 
MAPE:	 6.948265794170055

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 153.59400995187858 
RMSE:	 12.39330504554288 
MAPE:	 11.203775482220726

KAMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 121.28941541171922 
RMSE:	 11.013147388994629 
MAPE:	 9.175643045864026

MIDPOINT
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	45.15% Accuracy
MSE:	 110.09412594018622 
RMSE:	 10.492574800314088 
MAPE:	 8.796456301428389
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19

Working on T3 predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.37 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4414.515, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3944.062, Time=0.05 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.35 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3715.173, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3577.471, Time=0.08 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.41 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.59 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3579.471, Time=0.19 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.160 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1784.736
Date:                Sun, 12 Dec 2021   AIC                           3577.471
Time:                        14:48:17   BIC                           3596.235
Sample:                             0   HQIC                          3584.677
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.844      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.861      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.862      0.000      -0.410      -0.387
sigma2         4.9242      0.023    215.469      0.000       4.879       4.969
===================================================================================
Ljung-Box (L1) (Q):                  14.55   Jarque-Bera (JB):           2468024.38
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       274.15
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.03602, saving model to LSTM2.h5
43/43 - 4s - loss: 0.1500 - accuracy: 0.0000e+00 - val_loss: 0.0360 - val_accuracy: 0.0037 - lr: 0.0010 - 4s/epoch - 84ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.03602 to 0.01139, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0309 - accuracy: 0.0000e+00 - val_loss: 0.0114 - val_accuracy: 0.0037 - lr: 0.0010 - 274ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.01139
43/43 - 0s - loss: 0.0364 - accuracy: 0.0000e+00 - val_loss: 0.0897 - val_accuracy: 0.0037 - lr: 0.0010 - 262ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.01139
43/43 - 0s - loss: 0.0438 - accuracy: 0.0000e+00 - val_loss: 0.0251 - val_accuracy: 0.0037 - lr: 0.0010 - 252ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.01139
43/43 - 0s - loss: 0.0158 - accuracy: 0.0000e+00 - val_loss: 0.0613 - val_accuracy: 0.0037 - lr: 0.0010 - 274ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.01139
43/43 - 0s - loss: 0.0117 - accuracy: 0.0000e+00 - val_loss: 0.0312 - val_accuracy: 0.0037 - lr: 0.0010 - 281ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00007: val_loss did not improve from 0.01139
43/43 - 0s - loss: 0.0083 - accuracy: 0.0000e+00 - val_loss: 0.0216 - val_accuracy: 0.0037 - lr: 0.0010 - 255ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.01139 to 0.00638, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0146 - accuracy: 0.0000e+00 - val_loss: 0.0064 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 256ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.00638 to 0.00515, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0029 - accuracy: 0.0000e+00 - val_loss: 0.0051 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 265ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.00515 to 0.00491, saving model to LSTM2.h5
43/43 - 0s - loss: 0.0026 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 319ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0023 - accuracy: 0.0000e+00 - val_loss: 0.0053 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 236ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0021 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 277ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0019 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 291ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 237ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00015: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 236ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0076 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 292ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 246ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 234ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 254ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00020: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 252ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 241ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 269ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 249ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 256ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 252ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 288ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 251ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 240ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 259ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 256ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 250ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 254ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 241ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 275ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 257ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 283ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 238ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 238ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 242ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 241ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0071 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 261ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0071 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 270ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0071 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 258ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0071 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 257ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0070 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 295ms/epoch - 7ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0070 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 254ms/epoch - 6ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0070 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 245ms/epoch - 6ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0070 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 288ms/epoch - 7ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0069 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 254ms/epoch - 6ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0069 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 241ms/epoch - 6ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0069 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 256ms/epoch - 6ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0068 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 277ms/epoch - 6ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0068 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 256ms/epoch - 6ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00491
43/43 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0068 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 00060: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 75.20110458138421 
RMSE:	 8.67185704341257 
MAPE:	 7.0799160587584336

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 61.82384712230415 
RMSE:	 7.862814198638052 
MAPE:	 6.504666247736678

WMA
Prediction vs Close:		56.34% Accuracy
Prediction vs Prediction:	45.52% Accuracy
MSE:	 78.06346997131263 
RMSE:	 8.835353415190172 
MAPE:	 6.948265794170055

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 153.59400995187858 
RMSE:	 12.39330504554288 
MAPE:	 11.203775482220726

KAMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 121.28941541171922 
RMSE:	 11.013147388994629 
MAPE:	 9.175643045864026

MIDPOINT
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	45.15% Accuracy
MSE:	 110.09412594018622 
RMSE:	 10.492574800314088 
MAPE:	 8.796456301428389

T3
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	49.63% Accuracy
MSE:	 225.73907153615718 
RMSE:	 15.024615520410403 
MAPE:	 12.611725131734374
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9

Working on TEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.44 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4352.703, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3889.412, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.29 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3689.930, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3574.245, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.16 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.77 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3576.245, Time=0.19 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.078 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1783.123
Date:                Sun, 12 Dec 2021   AIC                           3574.245
Time:                        14:49:45   BIC                           3593.008
Sample:                             0   HQIC                          3581.451
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1480      0.004   -302.430      0.000      -1.155      -1.141
ar.L2         -0.8300      0.008    -99.682      0.000      -0.846      -0.814
ar.L3         -0.3687      0.007    -50.527      0.000      -0.383      -0.354
sigma2         4.9055      0.028    175.970      0.000       4.851       4.960
===================================================================================
Ljung-Box (L1) (Q):                  11.61   Jarque-Bera (JB):           1261976.58
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.16   Skew:                             2.52
Prob(H) (two-sided):                  0.00   Kurtosis:                       196.90
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.32785, saving model to LSTM2.h5
90/90 - 4s - loss: 0.0549 - accuracy: 0.0000e+00 - val_loss: 0.3279 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 4s/epoch - 45ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.32785 to 0.05194, saving model to LSTM2.h5
90/90 - 1s - loss: 0.0650 - accuracy: 0.0000e+00 - val_loss: 0.0519 - val_accuracy: 0.0037 - lr: 0.0010 - 562ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.05194
90/90 - 0s - loss: 0.0748 - accuracy: 0.0000e+00 - val_loss: 0.0536 - val_accuracy: 0.0037 - lr: 0.0010 - 489ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.05194 to 0.00511, saving model to LSTM2.h5
90/90 - 0s - loss: 0.0452 - accuracy: 0.0000e+00 - val_loss: 0.0051 - val_accuracy: 0.0037 - lr: 0.0010 - 482ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0236 - accuracy: 0.0000e+00 - val_loss: 0.0153 - val_accuracy: 0.0037 - lr: 0.0010 - 561ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0182 - accuracy: 0.0000e+00 - val_loss: 0.0166 - val_accuracy: 0.0037 - lr: 0.0010 - 492ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0196 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 0.0010 - 499ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0200 - accuracy: 0.0000e+00 - val_loss: 0.0336 - val_accuracy: 0.0037 - lr: 0.0010 - 539ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00009: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0246 - accuracy: 0.0000e+00 - val_loss: 0.0255 - val_accuracy: 0.0037 - lr: 0.0010 - 567ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0381 - accuracy: 0.0000e+00 - val_loss: 0.0348 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 482ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0083 - accuracy: 0.0000e+00 - val_loss: 0.0203 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 476ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0068 - accuracy: 0.0000e+00 - val_loss: 0.0155 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 501ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0057 - accuracy: 0.0000e+00 - val_loss: 0.0135 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 475ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00014: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0048 - accuracy: 0.0000e+00 - val_loss: 0.0126 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 489ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0037 - accuracy: 0.0000e+00 - val_loss: 0.0118 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 522ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0035 - accuracy: 0.0000e+00 - val_loss: 0.0112 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 491ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0034 - accuracy: 0.0000e+00 - val_loss: 0.0108 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 565ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0033 - accuracy: 0.0000e+00 - val_loss: 0.0104 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 499ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00019: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0032 - accuracy: 0.0000e+00 - val_loss: 0.0102 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 455ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0032 - accuracy: 0.0000e+00 - val_loss: 0.0100 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 572ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0031 - accuracy: 0.0000e+00 - val_loss: 0.0098 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 535ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0030 - accuracy: 0.0000e+00 - val_loss: 0.0097 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 558ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0030 - accuracy: 0.0000e+00 - val_loss: 0.0096 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 465ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0029 - accuracy: 0.0000e+00 - val_loss: 0.0094 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 509ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0028 - accuracy: 0.0000e+00 - val_loss: 0.0093 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 455ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0028 - accuracy: 0.0000e+00 - val_loss: 0.0092 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 507ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0027 - accuracy: 0.0000e+00 - val_loss: 0.0091 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 486ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0027 - accuracy: 0.0000e+00 - val_loss: 0.0090 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 581ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0026 - accuracy: 0.0000e+00 - val_loss: 0.0089 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 465ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0025 - accuracy: 0.0000e+00 - val_loss: 0.0088 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 557ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0025 - accuracy: 0.0000e+00 - val_loss: 0.0087 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 473ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0024 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 516ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0024 - accuracy: 0.0000e+00 - val_loss: 0.0086 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 457ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0023 - accuracy: 0.0000e+00 - val_loss: 0.0085 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 504ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0022 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 535ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0022 - accuracy: 0.0000e+00 - val_loss: 0.0083 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 575ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0021 - accuracy: 0.0000e+00 - val_loss: 0.0082 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 467ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0021 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 491ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0020 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 541ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0019 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 488ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0019 - accuracy: 0.0000e+00 - val_loss: 0.0078 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 467ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0077 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 491ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0075 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 468ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0074 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 521ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 540ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0072 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 550ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0070 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 473ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0069 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 490ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0068 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 579ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0066 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 472ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0065 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 523ms/epoch - 6ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0063 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 488ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00511
90/90 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0062 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 472ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00511
90/90 - 1s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 560ms/epoch - 6ms/step
Epoch 00054: early stopping

SMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 75.20110458138421 
RMSE:	 8.67185704341257 
MAPE:	 7.0799160587584336

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	44.78% Accuracy
MSE:	 61.82384712230415 
RMSE:	 7.862814198638052 
MAPE:	 6.504666247736678

WMA
Prediction vs Close:		56.34% Accuracy
Prediction vs Prediction:	45.52% Accuracy
MSE:	 78.06346997131263 
RMSE:	 8.835353415190172 
MAPE:	 6.948265794170055

DEMA
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 153.59400995187858 
RMSE:	 12.39330504554288 
MAPE:	 11.203775482220726

KAMA
Prediction vs Close:		52.61% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 121.28941541171922 
RMSE:	 11.013147388994629 
MAPE:	 9.175643045864026

MIDPOINT
Prediction vs Close:		52.24% Accuracy
Prediction vs Prediction:	45.15% Accuracy
MSE:	 110.09412594018622 
RMSE:	 10.492574800314088 
MAPE:	 8.796456301428389

T3
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	49.63% Accuracy
MSE:	 225.73907153615718 
RMSE:	 15.024615520410403 
MAPE:	 12.611725131734374

TEMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 157.04980120863047 
RMSE:	 12.531951213144364 
MAPE:	 11.294114614846999
Runtime: mins: 12.02286981541666

Architecture Used¶

from google.colab import files
import cv2
uploaded = files.upload()

img = cv2.imread('Experiment2.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)

<matplotlib.image.AxesImage at 0x7fa5d05a45d0>

Model Plots¶

for i in range(len(list(simulation2.keys()))):
  SIM = list(simulation2.keys())[i]
  plot_train(simulation2,SIM)
  plot_test(simulation2,SIM)

----- Train RMSE for SMA ----- 8.871298903186338
----- Train_MSE_LSTM for SMA ----- 78.69994422967511
----- Train MAE LSTM for SMA ----- 7.764003126570808

----- Test RMSE for SMA----- 8.67185704341257
----- Test_MSE_LSTM for SMA----- 75.20110458138421
----- Test_MAE_LSTM for SMA----- 7.0799160587584336

----- Train RMSE for EMA ----- 10.179800509177445
----- Train_MSE_LSTM for EMA ----- 103.62833840664938
----- Train MAE LSTM for EMA ----- 8.952723233047472

----- Test RMSE for EMA----- 7.862814198638052
----- Test_MSE_LSTM for EMA----- 61.82384712230415
----- Test_MAE_LSTM for EMA----- 6.504666247736678

----- Train RMSE for WMA ----- 10.496291718330035
----- Train_MSE_LSTM for WMA ----- 110.17213983628366
----- Train MAE LSTM for WMA ----- 9.343427695739683

----- Test RMSE for WMA----- 8.835353415190172
----- Test_MSE_LSTM for WMA----- 78.06346997131263
----- Test_MAE_LSTM for WMA----- 6.948265794170055

----- Train RMSE for DEMA ----- 12.115569265976841
----- Train_MSE_LSTM for DEMA ----- 146.7870186386826
----- Train MAE LSTM for DEMA ----- 10.916550872639965

----- Test RMSE for DEMA----- 12.39330504554288
----- Test_MSE_LSTM for DEMA----- 153.59400995187858
----- Test_MAE_LSTM for DEMA----- 11.203775482220726

----- Train RMSE for KAMA ----- 10.558696520648454
----- Train_MSE_LSTM for KAMA ----- 111.48607221515375
----- Train MAE LSTM for KAMA ----- 9.496371790900133

----- Test RMSE for KAMA----- 11.013147388994629
----- Test_MSE_LSTM for KAMA----- 121.28941541171922
----- Test_MAE_LSTM for KAMA----- 9.175643045864026

Univariate Arima Multistep MutiVariate LSTM Hybrid Model Experiment 3¶

def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det = 20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # # Option 1
    # # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    # model.add(Dense(units=64,activation='relu'))
    # model.add(Dropout(0.5))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    # ## Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()


    # # option 2
    # model = Sequential()
    # model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    # model.add(Dense(64))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()




    # Option 3
    # define custom activation
    # reference: https://github.com/Vaibhav-Sachdeva/Correlation-Coefficient-Prediction-using-ARIMA-LSTM-Hybrid-Model/blob/main/Code/LSTM-ARIMA.ipynb
    class Double_Tanh(Activation):
        def __init__(self, activation, **kwargs):
            super(Double_Tanh, self).__init__(activation, **kwargs)
            self.__name__ = 'double_tanh'

    def double_tanh(x):
        return (K.tanh(x) * 2)

    get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
        # Model Generation
    model = Sequential()
    #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    model.add(Dense(1))
    model.add(Activation(double_tanh))
    model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM3.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(x_train.shape[1], 1)))
    # model.add(LSTM(units=int(lstm_len/2)))
    # model.add(Dense(1, activation='sigmoid'))
    # model.compile(loss='mean_squared_error', optimizer='adam')
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te

if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation3 = {}
    imgfile = 'Experiment3'
    for ma in optimized_period:
              print(ma)
              print(functions[ma])
              print ( int( optimized_period[ma]))
            # if ma == 'SMA':
              low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
              low_vol = low_vol.fillna(0)
              low_vol_data = df['close']
              high_vol = pd.DataFrame()
              df2 = df.copy()
              for i in df2.columns:
                if i in low_vol.columns:
                  high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
              high_vol_data = df['close']
              ## *****************************************************
              # Generate ARIMA and LSTM predictions
              print('\nWorking on ' + ma + ' predictions')
              try:
                print('parameters used : ', train_len, test_len)
                low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima(low_vol,low_vol_data, train_len, test_len)
              except:
                  print('ARIMA error, skipping to next MA type')
                  continue
              Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
              final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
              mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
              rmse_ftr = mse_ftr ** 0.5
              mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
              mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

              final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
              mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
              rmse = mse ** 0.5
              mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              # Generate prediction accuracy
              actual = df['close'].tail(test_len).values
              result_1 = []
              result_2 = []
              for i in range(1, len(final_prediction)):
                  # Compare prediction to previous close price
                  if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                      result_1.append(1)
                  elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                      result_1.append(1)
                  else:
                      result_1.append(0)

                  # Compare prediction to previous prediction
                  if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                      result_2.append(1)
                  elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                      result_2.append(1)
                  else:
                      result_2.append(0)

              accuracy_1 = np.mean(result_1)
              accuracy_2 = np.mean(result_2)

              simulation3[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                            'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                            'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                            'rmse': rmse_ftr, 'mae' : mae_ftr},
                                'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                          'rmse': rmse, 'mae': mae },
                                'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

              # save simulation data here as checkpoint
              with open('simulation3_data.json', 'w') as fp:
                  json.dump(simulation3, fp)

              for ma in simulation3.keys():
                  print('\n' + ma)
                  print('Prediction vs Close:\t\t' + str(round(100*simulation3[ma]['accuracy']['prediction vs close'], 2))
                        + '% Accuracy')
                  print('Prediction vs Prediction:\t' + str(round(100*simulation3[ma]['accuracy']['prediction vs prediction'], 2))
                        + '% Accuracy')
                  print('MSE:\t', simulation3[ma]['final']['mse'],
                        '\nRMSE:\t', simulation3[ma]['final']['rmse'],
                        '\nMAPE:\t', simulation3[ma]['final']['mae'])#,
                        # '\nMAPE:\t', simulation[ma]['final']['mape'])
            # else:
            #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.51 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4157.020, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3687.148, Time=0.05 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.19 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3458.651, Time=0.08 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3322.133, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.77 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.82 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3324.133, Time=0.22 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.752 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1657.067
Date:                Sun, 12 Dec 2021   AIC                           3322.133
Time:                        14:57:27   BIC                           3340.897
Sample:                             0   HQIC                          3329.339
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1966      0.003   -387.226      0.000      -1.203      -1.191
ar.L2         -0.8952      0.006   -138.692      0.000      -0.908      -0.883
ar.L3         -0.3968      0.006    -68.284      0.000      -0.408      -0.385
sigma2         3.5858      0.017    214.535      0.000       3.553       3.619
===================================================================================
Ljung-Box (L1) (Q):                  14.47   Jarque-Bera (JB):           2428881.42
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       271.99
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.32523, saving model to LSTM3.h5
48/48 - 2s - loss: 0.2060 - mse: 0.2060 - mae: 0.3352 - val_loss: 0.3252 - val_mse: 0.3252 - val_mae: 0.5327 - lr: 0.0010 - 2s/epoch - 44ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.32523
48/48 - 0s - loss: 0.0738 - mse: 0.0738 - mae: 0.2252 - val_loss: 0.3958 - val_mse: 0.3958 - val_mae: 0.5963 - lr: 0.0010 - 193ms/epoch - 4ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.32523 to 0.31040, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0327 - mse: 0.0327 - mae: 0.1433 - val_loss: 0.3104 - val_mse: 0.3104 - val_mae: 0.5247 - lr: 0.0010 - 221ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.31040
48/48 - 0s - loss: 0.0236 - mse: 0.0236 - mae: 0.1211 - val_loss: 0.3787 - val_mse: 0.3787 - val_mae: 0.5870 - lr: 0.0010 - 212ms/epoch - 4ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.31040
48/48 - 0s - loss: 0.0182 - mse: 0.0182 - mae: 0.1046 - val_loss: 0.3283 - val_mse: 0.3283 - val_mae: 0.5451 - lr: 0.0010 - 229ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.31040
48/48 - 0s - loss: 0.0143 - mse: 0.0143 - mae: 0.0938 - val_loss: 0.3362 - val_mse: 0.3362 - val_mae: 0.5529 - lr: 0.0010 - 211ms/epoch - 4ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.31040 to 0.27120, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0125 - mse: 0.0125 - mae: 0.0880 - val_loss: 0.2712 - val_mse: 0.2712 - val_mae: 0.4936 - lr: 0.0010 - 260ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.27120
48/48 - 0s - loss: 0.0110 - mse: 0.0110 - mae: 0.0823 - val_loss: 0.3407 - val_mse: 0.3407 - val_mae: 0.5586 - lr: 0.0010 - 230ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.27120 to 0.24048, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0107 - mse: 0.0107 - mae: 0.0812 - val_loss: 0.2405 - val_mse: 0.2405 - val_mae: 0.4655 - lr: 0.0010 - 211ms/epoch - 4ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.24048
48/48 - 0s - loss: 0.0088 - mse: 0.0088 - mae: 0.0728 - val_loss: 0.3159 - val_mse: 0.3159 - val_mae: 0.5381 - lr: 0.0010 - 219ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.24048 to 0.21784, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0107 - mse: 0.0107 - mae: 0.0801 - val_loss: 0.2178 - val_mse: 0.2178 - val_mae: 0.4433 - lr: 0.0010 - 218ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.21784
48/48 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0702 - val_loss: 0.3228 - val_mse: 0.3228 - val_mae: 0.5467 - lr: 0.0010 - 228ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.21784 to 0.16075, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0090 - mse: 0.0090 - mae: 0.0751 - val_loss: 0.1608 - val_mse: 0.1608 - val_mae: 0.3764 - lr: 0.0010 - 248ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.16075
48/48 - 0s - loss: 0.0091 - mse: 0.0091 - mae: 0.0728 - val_loss: 0.3245 - val_mse: 0.3245 - val_mae: 0.5497 - lr: 0.0010 - 215ms/epoch - 4ms/step
Epoch 15/500

Epoch 00015: val_loss improved from 0.16075 to 0.10621, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0120 - mse: 0.0120 - mae: 0.0830 - val_loss: 0.1062 - val_mse: 0.1062 - val_mae: 0.2995 - lr: 0.0010 - 227ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.10621
48/48 - 0s - loss: 0.0146 - mse: 0.0146 - mae: 0.0872 - val_loss: 0.4383 - val_mse: 0.4383 - val_mae: 0.6444 - lr: 0.0010 - 210ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.10621 to 0.03004, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0200 - mse: 0.0200 - mae: 0.1034 - val_loss: 0.0300 - val_mse: 0.0300 - val_mae: 0.1374 - lr: 0.0010 - 254ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.03004
48/48 - 0s - loss: 0.0230 - mse: 0.0230 - mae: 0.1172 - val_loss: 0.4537 - val_mse: 0.4537 - val_mae: 0.6558 - lr: 0.0010 - 224ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss improved from 0.03004 to 0.02569, saving model to LSTM3.h5
48/48 - 0s - loss: 0.0254 - mse: 0.0254 - mae: 0.1215 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1258 - lr: 0.0010 - 237ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0249 - mse: 0.0249 - mae: 0.1271 - val_loss: 0.2785 - val_mse: 0.2785 - val_mae: 0.5097 - lr: 0.0010 - 242ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0161 - mse: 0.0161 - mae: 0.0976 - val_loss: 0.0512 - val_mse: 0.0512 - val_mae: 0.2018 - lr: 0.0010 - 247ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0134 - mse: 0.0134 - mae: 0.0941 - val_loss: 0.2064 - val_mse: 0.2064 - val_mae: 0.4377 - lr: 0.0010 - 226ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0090 - mse: 0.0090 - mae: 0.0746 - val_loss: 0.0759 - val_mse: 0.0759 - val_mae: 0.2555 - lr: 0.0010 - 219ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00024: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0089 - mse: 0.0089 - mae: 0.0760 - val_loss: 0.1579 - val_mse: 0.1579 - val_mae: 0.3803 - lr: 0.0010 - 277ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0103 - mse: 0.0103 - mae: 0.0805 - val_loss: 0.1393 - val_mse: 0.1393 - val_mae: 0.3563 - lr: 1.0000e-04 - 213ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0575 - val_loss: 0.1345 - val_mse: 0.1345 - val_mae: 0.3497 - lr: 1.0000e-04 - 231ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0585 - val_loss: 0.1325 - val_mse: 0.1325 - val_mae: 0.3469 - lr: 1.0000e-04 - 190ms/epoch - 4ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0550 - val_loss: 0.1280 - val_mse: 0.1280 - val_mae: 0.3404 - lr: 1.0000e-04 - 265ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00029: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0554 - val_loss: 0.1241 - val_mse: 0.1241 - val_mae: 0.3348 - lr: 1.0000e-04 - 234ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0536 - val_loss: 0.1242 - val_mse: 0.1242 - val_mae: 0.3350 - lr: 1.0000e-05 - 198ms/epoch - 4ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0528 - val_loss: 0.1242 - val_mse: 0.1242 - val_mae: 0.3350 - lr: 1.0000e-05 - 203ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0536 - val_loss: 0.1243 - val_mse: 0.1243 - val_mae: 0.3352 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0526 - val_loss: 0.1242 - val_mse: 0.1242 - val_mae: 0.3349 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 34/500

Epoch 00034: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00034: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0525 - val_loss: 0.1239 - val_mse: 0.1239 - val_mae: 0.3346 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0525 - val_loss: 0.1238 - val_mse: 0.1238 - val_mae: 0.3344 - lr: 1.0000e-05 - 229ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0520 - val_loss: 0.1239 - val_mse: 0.1239 - val_mae: 0.3345 - lr: 1.0000e-05 - 233ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0542 - val_loss: 0.1234 - val_mse: 0.1234 - val_mae: 0.3338 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0534 - val_loss: 0.1232 - val_mse: 0.1232 - val_mae: 0.3336 - lr: 1.0000e-05 - 228ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0538 - val_loss: 0.1230 - val_mse: 0.1230 - val_mae: 0.3333 - lr: 1.0000e-05 - 231ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0523 - val_loss: 0.1227 - val_mse: 0.1227 - val_mae: 0.3328 - lr: 1.0000e-05 - 231ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0552 - val_loss: 0.1222 - val_mse: 0.1222 - val_mae: 0.3321 - lr: 1.0000e-05 - 250ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0534 - val_loss: 0.1219 - val_mse: 0.1219 - val_mae: 0.3316 - lr: 1.0000e-05 - 203ms/epoch - 4ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0497 - val_loss: 0.1215 - val_mse: 0.1215 - val_mae: 0.3310 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0530 - val_loss: 0.1214 - val_mse: 0.1214 - val_mae: 0.3310 - lr: 1.0000e-05 - 202ms/epoch - 4ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0521 - val_loss: 0.1215 - val_mse: 0.1215 - val_mae: 0.3311 - lr: 1.0000e-05 - 229ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0503 - val_loss: 0.1214 - val_mse: 0.1214 - val_mae: 0.3309 - lr: 1.0000e-05 - 228ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0531 - val_loss: 0.1215 - val_mse: 0.1215 - val_mae: 0.3311 - lr: 1.0000e-05 - 207ms/epoch - 4ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0514 - val_loss: 0.1218 - val_mse: 0.1218 - val_mae: 0.3315 - lr: 1.0000e-05 - 209ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0517 - val_loss: 0.1214 - val_mse: 0.1214 - val_mae: 0.3309 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0541 - val_loss: 0.1213 - val_mse: 0.1213 - val_mae: 0.3308 - lr: 1.0000e-05 - 255ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0514 - val_loss: 0.1213 - val_mse: 0.1213 - val_mae: 0.3308 - lr: 1.0000e-05 - 199ms/epoch - 4ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0512 - val_loss: 0.1209 - val_mse: 0.1209 - val_mae: 0.3302 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0504 - val_loss: 0.1204 - val_mse: 0.1204 - val_mae: 0.3295 - lr: 1.0000e-05 - 192ms/epoch - 4ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0526 - val_loss: 0.1201 - val_mse: 0.1201 - val_mae: 0.3290 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0522 - val_loss: 0.1200 - val_mse: 0.1200 - val_mae: 0.3289 - lr: 1.0000e-05 - 207ms/epoch - 4ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0515 - val_loss: 0.1203 - val_mse: 0.1203 - val_mae: 0.3293 - lr: 1.0000e-05 - 240ms/epoch - 5ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0519 - val_loss: 0.1200 - val_mse: 0.1200 - val_mae: 0.3290 - lr: 1.0000e-05 - 216ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0509 - val_loss: 0.1202 - val_mse: 0.1202 - val_mae: 0.3293 - lr: 1.0000e-05 - 219ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0502 - val_loss: 0.1209 - val_mse: 0.1209 - val_mae: 0.3303 - lr: 1.0000e-05 - 234ms/epoch - 5ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0527 - val_loss: 0.1206 - val_mse: 0.1206 - val_mae: 0.3298 - lr: 1.0000e-05 - 242ms/epoch - 5ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0501 - val_loss: 0.1202 - val_mse: 0.1202 - val_mae: 0.3293 - lr: 1.0000e-05 - 206ms/epoch - 4ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0500 - val_loss: 0.1200 - val_mse: 0.1200 - val_mae: 0.3290 - lr: 1.0000e-05 - 229ms/epoch - 5ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0480 - val_loss: 0.1194 - val_mse: 0.1194 - val_mae: 0.3281 - lr: 1.0000e-05 - 257ms/epoch - 5ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0533 - val_loss: 0.1189 - val_mse: 0.1189 - val_mae: 0.3274 - lr: 1.0000e-05 - 228ms/epoch - 5ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0505 - val_loss: 0.1182 - val_mse: 0.1182 - val_mae: 0.3264 - lr: 1.0000e-05 - 254ms/epoch - 5ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0496 - val_loss: 0.1185 - val_mse: 0.1185 - val_mae: 0.3269 - lr: 1.0000e-05 - 205ms/epoch - 4ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0498 - val_loss: 0.1183 - val_mse: 0.1183 - val_mae: 0.3265 - lr: 1.0000e-05 - 209ms/epoch - 4ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0514 - val_loss: 0.1178 - val_mse: 0.1178 - val_mae: 0.3257 - lr: 1.0000e-05 - 209ms/epoch - 4ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.02569
48/48 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0498 - val_loss: 0.1180 - val_mse: 0.1180 - val_mae: 0.3261 - lr: 1.0000e-05 - 230ms/epoch - 5ms/step
Epoch 00069: early stopping

SMA
Prediction vs Close:		51.49% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 32.725767438505336 
RMSE:	 5.7206439706125165 
MAPE:	 4.798603095387009
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.41 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4231.556, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3761.238, Time=0.05 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.27 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3532.227, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3394.496, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.87 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.62 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3396.496, Time=0.21 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.621 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1693.248
Date:                Sun, 12 Dec 2021   AIC                           3394.496
Time:                        14:58:57   BIC                           3413.260
Sample:                             0   HQIC                          3401.702
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.569      0.000      -1.204      -1.192
ar.L2         -0.8976      0.006   -139.811      0.000      -0.910      -0.885
ar.L3         -0.3984      0.006    -68.662      0.000      -0.410      -0.387
sigma2         3.9230      0.018    215.372      0.000       3.887       3.959
===================================================================================
Ljung-Box (L1) (Q):                  14.54   Jarque-Bera (JB):           2462173.05
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.82
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.15984, saving model to LSTM3.h5
16/16 - 2s - loss: 0.1221 - mse: 0.1221 - mae: 0.2728 - val_loss: 0.1598 - val_mse: 0.1598 - val_mae: 0.3529 - lr: 0.0010 - 2s/epoch - 156ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.15984 to 0.11744, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0788 - mse: 0.0788 - mae: 0.2263 - val_loss: 0.1174 - val_mse: 0.1174 - val_mae: 0.2992 - lr: 0.0010 - 93ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.11744 to 0.08186, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0321 - mse: 0.0321 - mae: 0.1422 - val_loss: 0.0819 - val_mse: 0.0819 - val_mae: 0.2447 - lr: 0.0010 - 97ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.08186 to 0.05965, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0213 - mse: 0.0213 - mae: 0.1188 - val_loss: 0.0596 - val_mse: 0.0596 - val_mae: 0.2041 - lr: 0.0010 - 92ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.05965 to 0.05652, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0213 - mse: 0.0213 - mae: 0.1151 - val_loss: 0.0565 - val_mse: 0.0565 - val_mae: 0.1988 - lr: 0.0010 - 103ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.05652 to 0.04919, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0131 - mse: 0.0131 - mae: 0.0893 - val_loss: 0.0492 - val_mse: 0.0492 - val_mae: 0.1834 - lr: 0.0010 - 104ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.04919 to 0.04071, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0124 - mse: 0.0124 - mae: 0.0874 - val_loss: 0.0407 - val_mse: 0.0407 - val_mae: 0.1639 - lr: 0.0010 - 106ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.04071 to 0.03576, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0099 - mse: 0.0099 - mae: 0.0778 - val_loss: 0.0358 - val_mse: 0.0358 - val_mae: 0.1518 - lr: 0.0010 - 105ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.03576
16/16 - 0s - loss: 0.0111 - mse: 0.0111 - mae: 0.0812 - val_loss: 0.0411 - val_mse: 0.0411 - val_mae: 0.1654 - lr: 0.0010 - 91ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.03576
16/16 - 0s - loss: 0.0097 - mse: 0.0097 - mae: 0.0784 - val_loss: 0.0360 - val_mse: 0.0360 - val_mae: 0.1526 - lr: 0.0010 - 80ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.03576 to 0.03549, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0091 - mse: 0.0091 - mae: 0.0742 - val_loss: 0.0355 - val_mse: 0.0355 - val_mae: 0.1519 - lr: 0.0010 - 107ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0086 - mse: 0.0086 - mae: 0.0721 - val_loss: 0.0411 - val_mse: 0.0411 - val_mae: 0.1674 - lr: 0.0010 - 88ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0675 - val_loss: 0.0394 - val_mse: 0.0394 - val_mae: 0.1635 - lr: 0.0010 - 79ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0670 - val_loss: 0.0397 - val_mse: 0.0397 - val_mae: 0.1653 - lr: 0.0010 - 86ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0654 - val_loss: 0.0361 - val_mse: 0.0361 - val_mae: 0.1563 - lr: 0.0010 - 82ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00016: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0648 - val_loss: 0.0424 - val_mse: 0.0424 - val_mae: 0.1744 - lr: 0.0010 - 87ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0627 - val_loss: 0.0419 - val_mse: 0.0419 - val_mae: 0.1733 - lr: 1.0000e-04 - 96ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0632 - val_loss: 0.0410 - val_mse: 0.0410 - val_mae: 0.1711 - lr: 1.0000e-04 - 94ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0645 - val_loss: 0.0397 - val_mse: 0.0397 - val_mae: 0.1678 - lr: 1.0000e-04 - 79ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0624 - val_loss: 0.0391 - val_mse: 0.0391 - val_mae: 0.1660 - lr: 1.0000e-04 - 78ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00021: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0644 - val_loss: 0.0389 - val_mse: 0.0389 - val_mae: 0.1658 - lr: 1.0000e-04 - 90ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0606 - val_loss: 0.0388 - val_mse: 0.0388 - val_mae: 0.1655 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0627 - val_loss: 0.0387 - val_mse: 0.0387 - val_mae: 0.1652 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0638 - val_loss: 0.0386 - val_mse: 0.0386 - val_mae: 0.1650 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0600 - val_loss: 0.0386 - val_mse: 0.0386 - val_mae: 0.1647 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00026: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0589 - val_loss: 0.0384 - val_mse: 0.0384 - val_mae: 0.1644 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0589 - val_loss: 0.0384 - val_mse: 0.0384 - val_mae: 0.1643 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0623 - val_loss: 0.0384 - val_mse: 0.0384 - val_mae: 0.1642 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0606 - val_loss: 0.0383 - val_mse: 0.0383 - val_mae: 0.1640 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0595 - val_loss: 0.0381 - val_mse: 0.0381 - val_mae: 0.1636 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0633 - val_loss: 0.0382 - val_mse: 0.0382 - val_mae: 0.1637 - lr: 1.0000e-05 - 131ms/epoch - 8ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0637 - val_loss: 0.0381 - val_mse: 0.0381 - val_mae: 0.1635 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0591 - val_loss: 0.0379 - val_mse: 0.0379 - val_mae: 0.1631 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0639 - val_loss: 0.0379 - val_mse: 0.0379 - val_mae: 0.1629 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0600 - val_loss: 0.0378 - val_mse: 0.0378 - val_mae: 0.1628 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0627 - val_loss: 0.0377 - val_mse: 0.0377 - val_mae: 0.1624 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0624 - val_loss: 0.0376 - val_mse: 0.0376 - val_mae: 0.1621 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0596 - val_loss: 0.0374 - val_mse: 0.0374 - val_mae: 0.1618 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0617 - val_loss: 0.0374 - val_mse: 0.0374 - val_mae: 0.1616 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0627 - val_loss: 0.0373 - val_mse: 0.0373 - val_mae: 0.1613 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0633 - val_loss: 0.0372 - val_mse: 0.0372 - val_mae: 0.1610 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0607 - val_loss: 0.0370 - val_mse: 0.0370 - val_mae: 0.1606 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0602 - val_loss: 0.0369 - val_mse: 0.0369 - val_mae: 0.1604 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0610 - val_loss: 0.0369 - val_mse: 0.0369 - val_mae: 0.1603 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0629 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1602 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0616 - val_loss: 0.0367 - val_mse: 0.0367 - val_mae: 0.1598 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0608 - val_loss: 0.0365 - val_mse: 0.0365 - val_mae: 0.1593 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0595 - val_loss: 0.0364 - val_mse: 0.0364 - val_mae: 0.1589 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0621 - val_loss: 0.0362 - val_mse: 0.0362 - val_mae: 0.1585 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0637 - val_loss: 0.0361 - val_mse: 0.0361 - val_mae: 0.1582 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0589 - val_loss: 0.0361 - val_mse: 0.0361 - val_mae: 0.1580 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0591 - val_loss: 0.0360 - val_mse: 0.0360 - val_mae: 0.1578 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0608 - val_loss: 0.0359 - val_mse: 0.0359 - val_mae: 0.1575 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0620 - val_loss: 0.0359 - val_mse: 0.0359 - val_mae: 0.1575 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0618 - val_loss: 0.0358 - val_mse: 0.0358 - val_mae: 0.1573 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0615 - val_loss: 0.0357 - val_mse: 0.0357 - val_mae: 0.1570 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0628 - val_loss: 0.0356 - val_mse: 0.0356 - val_mae: 0.1567 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.03549
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0619 - val_loss: 0.0355 - val_mse: 0.0355 - val_mae: 0.1565 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss improved from 0.03549 to 0.03541, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0616 - val_loss: 0.0354 - val_mse: 0.0354 - val_mae: 0.1562 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 60/500

Epoch 00060: val_loss improved from 0.03541 to 0.03537, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0584 - val_loss: 0.0354 - val_mse: 0.0354 - val_mae: 0.1561 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 61/500

Epoch 00061: val_loss improved from 0.03537 to 0.03535, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0631 - val_loss: 0.0353 - val_mse: 0.0353 - val_mae: 0.1561 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 62/500

Epoch 00062: val_loss improved from 0.03535 to 0.03528, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0583 - val_loss: 0.0353 - val_mse: 0.0353 - val_mae: 0.1559 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 63/500

Epoch 00063: val_loss improved from 0.03528 to 0.03526, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0563 - val_loss: 0.0353 - val_mse: 0.0353 - val_mae: 0.1559 - lr: 1.0000e-05 - 127ms/epoch - 8ms/step
Epoch 64/500

Epoch 00064: val_loss improved from 0.03526 to 0.03525, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0621 - val_loss: 0.0352 - val_mse: 0.0352 - val_mae: 0.1558 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 65/500

Epoch 00065: val_loss improved from 0.03525 to 0.03522, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0628 - val_loss: 0.0352 - val_mse: 0.0352 - val_mae: 0.1558 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.03522
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0594 - val_loss: 0.0353 - val_mse: 0.0353 - val_mae: 0.1559 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.03522
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0634 - val_loss: 0.0353 - val_mse: 0.0353 - val_mae: 0.1561 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.03522
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0619 - val_loss: 0.0353 - val_mse: 0.0353 - val_mae: 0.1561 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.03522
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0617 - val_loss: 0.0352 - val_mse: 0.0352 - val_mae: 0.1559 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.03522
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0632 - val_loss: 0.0352 - val_mse: 0.0352 - val_mae: 0.1559 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 71/500

Epoch 00071: val_loss improved from 0.03522 to 0.03518, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0611 - val_loss: 0.0352 - val_mse: 0.0352 - val_mae: 0.1558 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 72/500

Epoch 00072: val_loss improved from 0.03518 to 0.03514, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0576 - val_loss: 0.0351 - val_mse: 0.0351 - val_mae: 0.1557 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.03514
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0599 - val_loss: 0.0352 - val_mse: 0.0352 - val_mae: 0.1557 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 74/500

Epoch 00074: val_loss improved from 0.03514 to 0.03513, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0625 - val_loss: 0.0351 - val_mse: 0.0351 - val_mae: 0.1557 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 75/500

Epoch 00075: val_loss improved from 0.03513 to 0.03511, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0577 - val_loss: 0.0351 - val_mse: 0.0351 - val_mae: 0.1557 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.03511
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0619 - val_loss: 0.0352 - val_mse: 0.0352 - val_mae: 0.1559 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 77/500

Epoch 00077: val_loss did not improve from 0.03511
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0596 - val_loss: 0.0352 - val_mse: 0.0352 - val_mae: 0.1559 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.03511
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0605 - val_loss: 0.0353 - val_mse: 0.0353 - val_mae: 0.1562 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 79/500

Epoch 00079: val_loss did not improve from 0.03511
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0603 - val_loss: 0.0351 - val_mse: 0.0351 - val_mae: 0.1559 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 80/500

Epoch 00080: val_loss improved from 0.03511 to 0.03500, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0588 - val_loss: 0.0350 - val_mse: 0.0350 - val_mae: 0.1554 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 81/500

Epoch 00081: val_loss did not improve from 0.03500
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0609 - val_loss: 0.0350 - val_mse: 0.0350 - val_mae: 0.1556 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 82/500

Epoch 00082: val_loss improved from 0.03500 to 0.03495, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0572 - val_loss: 0.0350 - val_mse: 0.0350 - val_mae: 0.1553 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 83/500

Epoch 00083: val_loss improved from 0.03495 to 0.03491, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0576 - val_loss: 0.0349 - val_mse: 0.0349 - val_mae: 0.1552 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 84/500

Epoch 00084: val_loss improved from 0.03491 to 0.03489, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0601 - val_loss: 0.0349 - val_mse: 0.0349 - val_mae: 0.1551 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 85/500

Epoch 00085: val_loss improved from 0.03489 to 0.03488, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0596 - val_loss: 0.0349 - val_mse: 0.0349 - val_mae: 0.1551 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 86/500

Epoch 00086: val_loss did not improve from 0.03488
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0611 - val_loss: 0.0349 - val_mse: 0.0349 - val_mae: 0.1553 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 87/500

Epoch 00087: val_loss did not improve from 0.03488
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0582 - val_loss: 0.0349 - val_mse: 0.0349 - val_mae: 0.1553 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 88/500

Epoch 00088: val_loss improved from 0.03488 to 0.03485, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0608 - val_loss: 0.0349 - val_mse: 0.0349 - val_mae: 0.1551 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 89/500

Epoch 00089: val_loss did not improve from 0.03485
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0579 - val_loss: 0.0349 - val_mse: 0.0349 - val_mae: 0.1552 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 90/500

Epoch 00090: val_loss improved from 0.03485 to 0.03481, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0580 - val_loss: 0.0348 - val_mse: 0.0348 - val_mae: 0.1550 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 91/500

Epoch 00091: val_loss improved from 0.03481 to 0.03474, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0612 - val_loss: 0.0347 - val_mse: 0.0347 - val_mae: 0.1548 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 92/500

Epoch 00092: val_loss improved from 0.03474 to 0.03465, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0599 - val_loss: 0.0347 - val_mse: 0.0347 - val_mae: 0.1546 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 93/500

Epoch 00093: val_loss improved from 0.03465 to 0.03462, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0594 - val_loss: 0.0346 - val_mse: 0.0346 - val_mae: 0.1545 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 94/500

Epoch 00094: val_loss did not improve from 0.03462
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0626 - val_loss: 0.0347 - val_mse: 0.0347 - val_mae: 0.1547 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 95/500

Epoch 00095: val_loss improved from 0.03462 to 0.03459, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0584 - val_loss: 0.0346 - val_mse: 0.0346 - val_mae: 0.1545 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 96/500

Epoch 00096: val_loss improved from 0.03459 to 0.03446, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0586 - val_loss: 0.0345 - val_mse: 0.0345 - val_mae: 0.1541 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 97/500

Epoch 00097: val_loss did not improve from 0.03446
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0577 - val_loss: 0.0345 - val_mse: 0.0345 - val_mae: 0.1542 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 98/500

Epoch 00098: val_loss did not improve from 0.03446
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0609 - val_loss: 0.0345 - val_mse: 0.0345 - val_mae: 0.1543 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 99/500

Epoch 00099: val_loss improved from 0.03446 to 0.03436, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0541 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1539 - lr: 1.0000e-05 - 151ms/epoch - 9ms/step
Epoch 100/500

Epoch 00100: val_loss improved from 0.03436 to 0.03424, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0569 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1536 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 101/500

Epoch 00101: val_loss improved from 0.03424 to 0.03420, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0594 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1534 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 102/500

Epoch 00102: val_loss improved from 0.03420 to 0.03407, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0604 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1531 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 103/500

Epoch 00103: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0612 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1534 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 104/500

Epoch 00104: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0594 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1533 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 105/500

Epoch 00105: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0644 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1533 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 106/500

Epoch 00106: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0632 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1534 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 107/500

Epoch 00107: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0609 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1533 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 108/500

Epoch 00108: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0601 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1536 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 109/500

Epoch 00109: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0610 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1541 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 110/500

Epoch 00110: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0583 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1541 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 111/500

Epoch 00111: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0580 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1543 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 112/500

Epoch 00112: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0612 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1544 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 113/500

Epoch 00113: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0591 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1543 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 114/500

Epoch 00114: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0599 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1544 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 115/500

Epoch 00115: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0601 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1540 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 116/500

Epoch 00116: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0609 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1537 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 117/500

Epoch 00117: val_loss did not improve from 0.03407
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0568 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1535 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 118/500

Epoch 00118: val_loss improved from 0.03407 to 0.03398, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0612 - val_loss: 0.0340 - val_mse: 0.0340 - val_mae: 0.1532 - lr: 1.0000e-05 - 116ms/epoch - 7ms/step
Epoch 119/500

Epoch 00119: val_loss improved from 0.03398 to 0.03383, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0609 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1527 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 120/500

Epoch 00120: val_loss improved from 0.03383 to 0.03373, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0586 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1524 - lr: 1.0000e-05 - 123ms/epoch - 8ms/step
Epoch 121/500

Epoch 00121: val_loss improved from 0.03373 to 0.03350, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0592 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1518 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 122/500

Epoch 00122: val_loss improved from 0.03350 to 0.03347, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0593 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1517 - lr: 1.0000e-05 - 126ms/epoch - 8ms/step
Epoch 123/500

Epoch 00123: val_loss improved from 0.03347 to 0.03329, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0621 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1512 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 124/500

Epoch 00124: val_loss improved from 0.03329 to 0.03309, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0597 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1506 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 125/500

Epoch 00125: val_loss improved from 0.03309 to 0.03303, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0594 - val_loss: 0.0330 - val_mse: 0.0330 - val_mae: 0.1504 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 126/500

Epoch 00126: val_loss did not improve from 0.03303
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0569 - val_loss: 0.0330 - val_mse: 0.0330 - val_mae: 0.1505 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 127/500

Epoch 00127: val_loss improved from 0.03303 to 0.03293, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0607 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1501 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 128/500

Epoch 00128: val_loss improved from 0.03293 to 0.03284, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0602 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1499 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 129/500

Epoch 00129: val_loss improved from 0.03284 to 0.03272, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0577 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1495 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 130/500

Epoch 00130: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0577 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1496 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 131/500

Epoch 00131: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0610 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1501 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 132/500

Epoch 00132: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0592 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1506 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 133/500

Epoch 00133: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0599 - val_loss: 0.0332 - val_mse: 0.0332 - val_mae: 0.1510 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 134/500

Epoch 00134: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0609 - val_loss: 0.0330 - val_mse: 0.0330 - val_mae: 0.1505 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 135/500

Epoch 00135: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0570 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1502 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 136/500

Epoch 00136: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0595 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1502 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 137/500

Epoch 00137: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0581 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1502 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 138/500

Epoch 00138: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0600 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1497 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 139/500

Epoch 00139: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0613 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1499 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 140/500

Epoch 00140: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0604 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1501 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 141/500

Epoch 00141: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0583 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1502 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 142/500

Epoch 00142: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0564 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1502 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 143/500

Epoch 00143: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0590 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1501 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 144/500

Epoch 00144: val_loss did not improve from 0.03272
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0568 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1500 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 145/500

Epoch 00145: val_loss improved from 0.03272 to 0.03264, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0591 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1496 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 146/500

Epoch 00146: val_loss improved from 0.03264 to 0.03260, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0568 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1495 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 147/500

Epoch 00147: val_loss improved from 0.03260 to 0.03258, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0565 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1495 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 148/500

Epoch 00148: val_loss improved from 0.03258 to 0.03241, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0555 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1490 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 149/500

Epoch 00149: val_loss improved from 0.03241 to 0.03226, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0561 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1485 - lr: 1.0000e-05 - 145ms/epoch - 9ms/step
Epoch 150/500

Epoch 00150: val_loss improved from 0.03226 to 0.03221, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0590 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1484 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 151/500

Epoch 00151: val_loss improved from 0.03221 to 0.03215, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0566 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1482 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 152/500

Epoch 00152: val_loss improved from 0.03215 to 0.03194, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0571 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1476 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 153/500

Epoch 00153: val_loss improved from 0.03194 to 0.03176, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0578 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1471 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 154/500

Epoch 00154: val_loss improved from 0.03176 to 0.03169, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0565 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1469 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 155/500

Epoch 00155: val_loss improved from 0.03169 to 0.03159, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0590 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1466 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 156/500

Epoch 00156: val_loss improved from 0.03159 to 0.03159, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0563 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1466 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 157/500

Epoch 00157: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0591 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1468 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 158/500

Epoch 00158: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0561 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1472 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 159/500

Epoch 00159: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0594 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1474 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 160/500

Epoch 00160: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0603 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1476 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 161/500

Epoch 00161: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0567 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1477 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 162/500

Epoch 00162: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0575 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1471 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 163/500

Epoch 00163: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0597 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1472 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 164/500

Epoch 00164: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0568 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1474 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 165/500

Epoch 00165: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0578 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1476 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 166/500

Epoch 00166: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0574 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1479 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 167/500

Epoch 00167: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0601 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1484 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 168/500

Epoch 00168: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0568 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1484 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 169/500

Epoch 00169: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0566 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1483 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 170/500

Epoch 00170: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0567 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1487 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 171/500

Epoch 00171: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0574 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1493 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 172/500

Epoch 00172: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0569 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1490 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 173/500

Epoch 00173: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0597 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1493 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 174/500

Epoch 00174: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0565 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1495 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 175/500

Epoch 00175: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0565 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1497 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 176/500

Epoch 00176: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0561 - val_loss: 0.0325 - val_mse: 0.0325 - val_mae: 0.1498 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 177/500

Epoch 00177: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0567 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1497 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 178/500

Epoch 00178: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0568 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1498 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 179/500

Epoch 00179: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0573 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1495 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 180/500

Epoch 00180: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0579 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1494 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 181/500

Epoch 00181: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0549 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1492 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 182/500

Epoch 00182: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0556 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1486 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 183/500

Epoch 00183: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0563 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1483 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 184/500

Epoch 00184: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0560 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1479 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 185/500

Epoch 00185: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0594 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1484 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 186/500

Epoch 00186: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0556 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1485 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 187/500

Epoch 00187: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0553 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1490 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 188/500

Epoch 00188: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0572 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1490 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 189/500

Epoch 00189: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0544 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1492 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 190/500

Epoch 00190: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0567 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1491 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 191/500

Epoch 00191: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0575 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1491 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 192/500

Epoch 00192: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0536 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1490 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 193/500

Epoch 00193: val_loss did not improve from 0.03159
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0569 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1478 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 194/500

Epoch 00194: val_loss improved from 0.03159 to 0.03145, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0589 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1471 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 195/500

Epoch 00195: val_loss improved from 0.03145 to 0.03107, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0560 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1460 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 196/500

Epoch 00196: val_loss improved from 0.03107 to 0.03085, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0565 - val_loss: 0.0309 - val_mse: 0.0309 - val_mae: 0.1453 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 197/500

Epoch 00197: val_loss did not improve from 0.03085
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0549 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1458 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 198/500

Epoch 00198: val_loss did not improve from 0.03085
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0578 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1463 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 199/500

Epoch 00199: val_loss did not improve from 0.03085
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0561 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1462 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 200/500

Epoch 00200: val_loss did not improve from 0.03085
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0558 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1460 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 201/500

Epoch 00201: val_loss did not improve from 0.03085
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0523 - val_loss: 0.0309 - val_mse: 0.0309 - val_mae: 0.1456 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 202/500

Epoch 00202: val_loss improved from 0.03085 to 0.03069, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0543 - val_loss: 0.0307 - val_mse: 0.0307 - val_mae: 0.1449 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 203/500

Epoch 00203: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0553 - val_loss: 0.0308 - val_mse: 0.0308 - val_mae: 0.1451 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 204/500

Epoch 00204: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0551 - val_loss: 0.0308 - val_mse: 0.0308 - val_mae: 0.1453 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 205/500

Epoch 00205: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0562 - val_loss: 0.0307 - val_mse: 0.0307 - val_mae: 0.1450 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 206/500

Epoch 00206: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0555 - val_loss: 0.0308 - val_mse: 0.0308 - val_mae: 0.1453 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 207/500

Epoch 00207: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0564 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1463 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 208/500

Epoch 00208: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0554 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1466 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 209/500

Epoch 00209: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0569 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1465 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 210/500

Epoch 00210: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0553 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1464 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 211/500

Epoch 00211: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0576 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1464 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 212/500

Epoch 00212: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0579 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1464 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 213/500

Epoch 00213: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0550 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1464 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 214/500

Epoch 00214: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0555 - val_loss: 0.0309 - val_mse: 0.0309 - val_mae: 0.1461 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 215/500

Epoch 00215: val_loss did not improve from 0.03069
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0544 - val_loss: 0.0308 - val_mse: 0.0308 - val_mae: 0.1455 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 216/500

Epoch 00216: val_loss improved from 0.03069 to 0.03062, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0552 - val_loss: 0.0306 - val_mse: 0.0306 - val_mae: 0.1451 - lr: 1.0000e-05 - 117ms/epoch - 7ms/step
Epoch 217/500

Epoch 00217: val_loss improved from 0.03062 to 0.03053, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0540 - val_loss: 0.0305 - val_mse: 0.0305 - val_mae: 0.1448 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 218/500

Epoch 00218: val_loss improved from 0.03053 to 0.03041, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0546 - val_loss: 0.0304 - val_mse: 0.0304 - val_mae: 0.1445 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 219/500

Epoch 00219: val_loss improved from 0.03041 to 0.03038, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0544 - val_loss: 0.0304 - val_mse: 0.0304 - val_mae: 0.1444 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 220/500

Epoch 00220: val_loss improved from 0.03038 to 0.03010, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0537 - val_loss: 0.0301 - val_mse: 0.0301 - val_mae: 0.1436 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 221/500

Epoch 00221: val_loss improved from 0.03010 to 0.02986, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0552 - val_loss: 0.0299 - val_mse: 0.0299 - val_mae: 0.1428 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 222/500

Epoch 00222: val_loss improved from 0.02986 to 0.02981, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0553 - val_loss: 0.0298 - val_mse: 0.0298 - val_mae: 0.1427 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 223/500

Epoch 00223: val_loss improved from 0.02981 to 0.02975, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0555 - val_loss: 0.0298 - val_mse: 0.0298 - val_mae: 0.1425 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 224/500

Epoch 00224: val_loss did not improve from 0.02975
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0543 - val_loss: 0.0298 - val_mse: 0.0298 - val_mae: 0.1427 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 225/500

Epoch 00225: val_loss did not improve from 0.02975
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0534 - val_loss: 0.0298 - val_mse: 0.0298 - val_mae: 0.1426 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 226/500

Epoch 00226: val_loss improved from 0.02975 to 0.02947, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0557 - val_loss: 0.0295 - val_mse: 0.0295 - val_mae: 0.1417 - lr: 1.0000e-05 - 138ms/epoch - 9ms/step
Epoch 227/500

Epoch 00227: val_loss did not improve from 0.02947
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0554 - val_loss: 0.0297 - val_mse: 0.0297 - val_mae: 0.1423 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 228/500

Epoch 00228: val_loss did not improve from 0.02947
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0550 - val_loss: 0.0297 - val_mse: 0.0297 - val_mae: 0.1424 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 229/500

Epoch 00229: val_loss did not improve from 0.02947
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0547 - val_loss: 0.0300 - val_mse: 0.0300 - val_mae: 0.1434 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 230/500

Epoch 00230: val_loss did not improve from 0.02947
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0566 - val_loss: 0.0299 - val_mse: 0.0299 - val_mae: 0.1433 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 231/500

Epoch 00231: val_loss did not improve from 0.02947
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0565 - val_loss: 0.0298 - val_mse: 0.0298 - val_mae: 0.1427 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 232/500

Epoch 00232: val_loss did not improve from 0.02947
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0560 - val_loss: 0.0296 - val_mse: 0.0296 - val_mae: 0.1424 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 233/500

Epoch 00233: val_loss did not improve from 0.02947
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0581 - val_loss: 0.0299 - val_mse: 0.0299 - val_mae: 0.1434 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 234/500

Epoch 00234: val_loss did not improve from 0.02947
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0530 - val_loss: 0.0301 - val_mse: 0.0301 - val_mae: 0.1439 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 235/500

Epoch 00235: val_loss did not improve from 0.02947
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0578 - val_loss: 0.0299 - val_mse: 0.0299 - val_mae: 0.1433 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 236/500

Epoch 00236: val_loss did not improve from 0.02947
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0546 - val_loss: 0.0295 - val_mse: 0.0295 - val_mae: 0.1421 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 237/500

Epoch 00237: val_loss did not improve from 0.02947
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0544 - val_loss: 0.0296 - val_mse: 0.0296 - val_mae: 0.1423 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 238/500

Epoch 00238: val_loss did not improve from 0.02947
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0550 - val_loss: 0.0295 - val_mse: 0.0295 - val_mae: 0.1420 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 239/500

Epoch 00239: val_loss improved from 0.02947 to 0.02932, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0550 - val_loss: 0.0293 - val_mse: 0.0293 - val_mae: 0.1415 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 240/500

Epoch 00240: val_loss improved from 0.02932 to 0.02924, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0544 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1413 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 241/500

Epoch 00241: val_loss improved from 0.02924 to 0.02923, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0546 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1413 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 242/500

Epoch 00242: val_loss improved from 0.02923 to 0.02921, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0549 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1412 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 243/500

Epoch 00243: val_loss improved from 0.02921 to 0.02917, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0554 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1411 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 244/500

Epoch 00244: val_loss improved from 0.02917 to 0.02916, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0548 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1411 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 245/500

Epoch 00245: val_loss improved from 0.02916 to 0.02912, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0548 - val_loss: 0.0291 - val_mse: 0.0291 - val_mae: 0.1410 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 246/500

Epoch 00246: val_loss did not improve from 0.02912
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0551 - val_loss: 0.0291 - val_mse: 0.0291 - val_mae: 0.1411 - lr: 1.0000e-05 - 124ms/epoch - 8ms/step
Epoch 247/500

Epoch 00247: val_loss did not improve from 0.02912
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0546 - val_loss: 0.0291 - val_mse: 0.0291 - val_mae: 0.1411 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 248/500

Epoch 00248: val_loss improved from 0.02912 to 0.02882, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0552 - val_loss: 0.0288 - val_mse: 0.0288 - val_mae: 0.1402 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 249/500

Epoch 00249: val_loss did not improve from 0.02882
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0568 - val_loss: 0.0289 - val_mse: 0.0289 - val_mae: 0.1403 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 250/500

Epoch 00250: val_loss did not improve from 0.02882
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0544 - val_loss: 0.0289 - val_mse: 0.0289 - val_mae: 0.1405 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 251/500

Epoch 00251: val_loss did not improve from 0.02882
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0552 - val_loss: 0.0289 - val_mse: 0.0289 - val_mae: 0.1404 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 252/500

Epoch 00252: val_loss improved from 0.02882 to 0.02875, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0554 - val_loss: 0.0288 - val_mse: 0.0288 - val_mae: 0.1400 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 253/500

Epoch 00253: val_loss did not improve from 0.02875
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0539 - val_loss: 0.0289 - val_mse: 0.0289 - val_mae: 0.1404 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 254/500

Epoch 00254: val_loss did not improve from 0.02875
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0564 - val_loss: 0.0288 - val_mse: 0.0288 - val_mae: 0.1402 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 255/500

Epoch 00255: val_loss improved from 0.02875 to 0.02866, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0544 - val_loss: 0.0287 - val_mse: 0.0287 - val_mae: 0.1398 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 256/500

Epoch 00256: val_loss did not improve from 0.02866
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0537 - val_loss: 0.0288 - val_mse: 0.0288 - val_mae: 0.1401 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 257/500

Epoch 00257: val_loss did not improve from 0.02866
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0518 - val_loss: 0.0289 - val_mse: 0.0289 - val_mae: 0.1407 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 258/500

Epoch 00258: val_loss did not improve from 0.02866
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0553 - val_loss: 0.0287 - val_mse: 0.0287 - val_mae: 0.1401 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 259/500

Epoch 00259: val_loss did not improve from 0.02866
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0576 - val_loss: 0.0288 - val_mse: 0.0288 - val_mae: 0.1404 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 260/500

Epoch 00260: val_loss did not improve from 0.02866
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0530 - val_loss: 0.0291 - val_mse: 0.0291 - val_mae: 0.1412 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 261/500

Epoch 00261: val_loss did not improve from 0.02866
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0535 - val_loss: 0.0291 - val_mse: 0.0291 - val_mae: 0.1414 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 262/500

Epoch 00262: val_loss did not improve from 0.02866
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0538 - val_loss: 0.0291 - val_mse: 0.0291 - val_mae: 0.1412 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 263/500

Epoch 00263: val_loss did not improve from 0.02866
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0508 - val_loss: 0.0288 - val_mse: 0.0288 - val_mae: 0.1403 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 264/500

Epoch 00264: val_loss did not improve from 0.02866
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0566 - val_loss: 0.0287 - val_mse: 0.0287 - val_mae: 0.1403 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 265/500

Epoch 00265: val_loss improved from 0.02866 to 0.02860, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0519 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1398 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 266/500

Epoch 00266: val_loss improved from 0.02860 to 0.02857, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0528 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1398 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 267/500

Epoch 00267: val_loss improved from 0.02857 to 0.02838, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0546 - val_loss: 0.0284 - val_mse: 0.0284 - val_mae: 0.1392 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 268/500

Epoch 00268: val_loss improved from 0.02838 to 0.02837, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0548 - val_loss: 0.0284 - val_mse: 0.0284 - val_mae: 0.1392 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 269/500

Epoch 00269: val_loss improved from 0.02837 to 0.02814, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0513 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1385 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 270/500

Epoch 00270: val_loss improved from 0.02814 to 0.02807, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0550 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1382 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 271/500

Epoch 00271: val_loss improved from 0.02807 to 0.02798, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0535 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1380 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 272/500

Epoch 00272: val_loss improved from 0.02798 to 0.02796, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0505 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1379 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 273/500

Epoch 00273: val_loss did not improve from 0.02796
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0524 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1381 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 274/500

Epoch 00274: val_loss improved from 0.02796 to 0.02790, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0526 - val_loss: 0.0279 - val_mse: 0.0279 - val_mae: 0.1378 - lr: 1.0000e-05 - 135ms/epoch - 8ms/step
Epoch 275/500

Epoch 00275: val_loss improved from 0.02790 to 0.02780, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0502 - val_loss: 0.0278 - val_mse: 0.0278 - val_mae: 0.1375 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 276/500

Epoch 00276: val_loss improved from 0.02780 to 0.02779, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0560 - val_loss: 0.0278 - val_mse: 0.0278 - val_mae: 0.1375 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 277/500

Epoch 00277: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0535 - val_loss: 0.0279 - val_mse: 0.0279 - val_mae: 0.1379 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 278/500

Epoch 00278: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0534 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1384 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 279/500

Epoch 00279: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0514 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1387 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 280/500

Epoch 00280: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0511 - val_loss: 0.0282 - val_mse: 0.0282 - val_mae: 0.1390 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 281/500

Epoch 00281: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0506 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1384 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 282/500

Epoch 00282: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0529 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1383 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 283/500

Epoch 00283: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0529 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1383 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 284/500

Epoch 00284: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0558 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1384 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 285/500

Epoch 00285: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0535 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1383 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 286/500

Epoch 00286: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0533 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1384 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 287/500

Epoch 00287: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0521 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1384 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 288/500

Epoch 00288: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0532 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1386 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 289/500

Epoch 00289: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0554 - val_loss: 0.0278 - val_mse: 0.0278 - val_mae: 0.1378 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 290/500

Epoch 00290: val_loss did not improve from 0.02779
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0537 - val_loss: 0.0278 - val_mse: 0.0278 - val_mae: 0.1378 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 291/500

Epoch 00291: val_loss improved from 0.02779 to 0.02743, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0531 - val_loss: 0.0274 - val_mse: 0.0274 - val_mae: 0.1366 - lr: 1.0000e-05 - 116ms/epoch - 7ms/step
Epoch 292/500

Epoch 00292: val_loss improved from 0.02743 to 0.02703, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0548 - val_loss: 0.0270 - val_mse: 0.0270 - val_mae: 0.1353 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 293/500

Epoch 00293: val_loss improved from 0.02703 to 0.02689, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0527 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1349 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 294/500

Epoch 00294: val_loss improved from 0.02689 to 0.02665, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0519 - val_loss: 0.0267 - val_mse: 0.0267 - val_mae: 0.1341 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 295/500

Epoch 00295: val_loss did not improve from 0.02665
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0517 - val_loss: 0.0267 - val_mse: 0.0267 - val_mae: 0.1344 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 296/500

Epoch 00296: val_loss improved from 0.02665 to 0.02661, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0554 - val_loss: 0.0266 - val_mse: 0.0266 - val_mae: 0.1340 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 297/500

Epoch 00297: val_loss did not improve from 0.02661
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0541 - val_loss: 0.0267 - val_mse: 0.0267 - val_mae: 0.1343 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 298/500

Epoch 00298: val_loss did not improve from 0.02661
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0527 - val_loss: 0.0268 - val_mse: 0.0268 - val_mae: 0.1349 - lr: 1.0000e-05 - 125ms/epoch - 8ms/step
Epoch 299/500

Epoch 00299: val_loss improved from 0.02661 to 0.02654, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0541 - val_loss: 0.0265 - val_mse: 0.0265 - val_mae: 0.1339 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 300/500

Epoch 00300: val_loss improved from 0.02654 to 0.02646, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0533 - val_loss: 0.0265 - val_mse: 0.0265 - val_mae: 0.1337 - lr: 1.0000e-05 - 117ms/epoch - 7ms/step
Epoch 301/500

Epoch 00301: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0524 - val_loss: 0.0266 - val_mse: 0.0266 - val_mae: 0.1342 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 302/500

Epoch 00302: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0556 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1350 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 303/500

Epoch 00303: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0493 - val_loss: 0.0271 - val_mse: 0.0271 - val_mae: 0.1357 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 304/500

Epoch 00304: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0551 - val_loss: 0.0271 - val_mse: 0.0271 - val_mae: 0.1357 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 305/500

Epoch 00305: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0506 - val_loss: 0.0272 - val_mse: 0.0272 - val_mae: 0.1360 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 306/500

Epoch 00306: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0518 - val_loss: 0.0271 - val_mse: 0.0271 - val_mae: 0.1359 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 307/500

Epoch 00307: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0531 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1352 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 308/500

Epoch 00308: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0494 - val_loss: 0.0271 - val_mse: 0.0271 - val_mae: 0.1360 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 309/500

Epoch 00309: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0516 - val_loss: 0.0271 - val_mse: 0.0271 - val_mae: 0.1359 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 310/500

Epoch 00310: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0544 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1352 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 311/500

Epoch 00311: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0541 - val_loss: 0.0267 - val_mse: 0.0267 - val_mae: 0.1348 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 312/500

Epoch 00312: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0514 - val_loss: 0.0270 - val_mse: 0.0270 - val_mae: 0.1355 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 313/500

Epoch 00313: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0530 - val_loss: 0.0272 - val_mse: 0.0272 - val_mae: 0.1365 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 314/500

Epoch 00314: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0502 - val_loss: 0.0273 - val_mse: 0.0273 - val_mae: 0.1368 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 315/500

Epoch 00315: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0508 - val_loss: 0.0276 - val_mse: 0.0276 - val_mae: 0.1375 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 316/500

Epoch 00316: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0549 - val_loss: 0.0274 - val_mse: 0.0274 - val_mae: 0.1372 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 317/500

Epoch 00317: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0509 - val_loss: 0.0272 - val_mse: 0.0272 - val_mae: 0.1365 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 318/500

Epoch 00318: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0525 - val_loss: 0.0270 - val_mse: 0.0270 - val_mae: 0.1359 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 319/500

Epoch 00319: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0509 - val_loss: 0.0266 - val_mse: 0.0266 - val_mae: 0.1344 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 320/500

Epoch 00320: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0541 - val_loss: 0.0267 - val_mse: 0.0267 - val_mae: 0.1348 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 321/500

Epoch 00321: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0521 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1356 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 322/500

Epoch 00322: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0558 - val_loss: 0.0268 - val_mse: 0.0268 - val_mae: 0.1352 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 323/500

Epoch 00323: val_loss did not improve from 0.02646
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0534 - val_loss: 0.0267 - val_mse: 0.0267 - val_mae: 0.1348 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 324/500

Epoch 00324: val_loss improved from 0.02646 to 0.02646, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0538 - val_loss: 0.0265 - val_mse: 0.0265 - val_mae: 0.1341 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 325/500

Epoch 00325: val_loss improved from 0.02646 to 0.02624, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0514 - val_loss: 0.0262 - val_mse: 0.0262 - val_mae: 0.1335 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 326/500

Epoch 00326: val_loss did not improve from 0.02624
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0549 - val_loss: 0.0264 - val_mse: 0.0264 - val_mae: 0.1339 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 327/500

Epoch 00327: val_loss did not improve from 0.02624
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0525 - val_loss: 0.0266 - val_mse: 0.0266 - val_mae: 0.1347 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 328/500

Epoch 00328: val_loss did not improve from 0.02624
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0513 - val_loss: 0.0264 - val_mse: 0.0264 - val_mae: 0.1341 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 329/500

Epoch 00329: val_loss improved from 0.02624 to 0.02613, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0509 - val_loss: 0.0261 - val_mse: 0.0261 - val_mae: 0.1331 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 330/500

Epoch 00330: val_loss improved from 0.02613 to 0.02586, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0517 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1323 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 331/500

Epoch 00331: val_loss improved from 0.02586 to 0.02575, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0471 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1319 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 332/500

Epoch 00332: val_loss improved from 0.02575 to 0.02561, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0503 - val_loss: 0.0256 - val_mse: 0.0256 - val_mae: 0.1315 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 333/500

Epoch 00333: val_loss improved from 0.02561 to 0.02540, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0516 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1308 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 334/500

Epoch 00334: val_loss improved from 0.02540 to 0.02523, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0537 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1303 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 335/500

Epoch 00335: val_loss did not improve from 0.02523
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0539 - val_loss: 0.0253 - val_mse: 0.0253 - val_mae: 0.1304 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 336/500

Epoch 00336: val_loss improved from 0.02523 to 0.02516, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0530 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1300 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 337/500

Epoch 00337: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0482 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1302 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 338/500

Epoch 00338: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0520 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1308 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 339/500

Epoch 00339: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0513 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1309 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 340/500

Epoch 00340: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0544 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1308 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 341/500

Epoch 00341: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0512 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1308 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 342/500

Epoch 00342: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0515 - val_loss: 0.0255 - val_mse: 0.0255 - val_mae: 0.1313 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 343/500

Epoch 00343: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0503 - val_loss: 0.0256 - val_mse: 0.0256 - val_mae: 0.1315 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 344/500

Epoch 00344: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0522 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1319 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 345/500

Epoch 00345: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0514 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1319 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 346/500

Epoch 00346: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0506 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1309 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 347/500

Epoch 00347: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0533 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1310 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 348/500

Epoch 00348: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0507 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1304 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 349/500

Epoch 00349: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0546 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1302 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 350/500

Epoch 00350: val_loss did not improve from 0.02516
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0488 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1305 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 351/500

Epoch 00351: val_loss improved from 0.02516 to 0.02512, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0520 - val_loss: 0.0251 - val_mse: 0.0251 - val_mae: 0.1301 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 352/500

Epoch 00352: val_loss improved from 0.02512 to 0.02486, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0529 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1293 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 353/500

Epoch 00353: val_loss did not improve from 0.02486
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0509 - val_loss: 0.0250 - val_mse: 0.0250 - val_mae: 0.1296 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 354/500

Epoch 00354: val_loss did not improve from 0.02486
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0528 - val_loss: 0.0251 - val_mse: 0.0251 - val_mae: 0.1301 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 355/500

Epoch 00355: val_loss did not improve from 0.02486
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0500 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1310 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 356/500

Epoch 00356: val_loss did not improve from 0.02486
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0529 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1312 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 357/500

Epoch 00357: val_loss did not improve from 0.02486
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0521 - val_loss: 0.0253 - val_mse: 0.0253 - val_mae: 0.1309 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 358/500

Epoch 00358: val_loss did not improve from 0.02486
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0521 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1304 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 359/500

Epoch 00359: val_loss did not improve from 0.02486
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0494 - val_loss: 0.0251 - val_mse: 0.0251 - val_mae: 0.1302 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 360/500

Epoch 00360: val_loss did not improve from 0.02486
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0514 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1310 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 361/500

Epoch 00361: val_loss did not improve from 0.02486
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0502 - val_loss: 0.0254 - val_mse: 0.0254 - val_mae: 0.1313 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 362/500

Epoch 00362: val_loss did not improve from 0.02486
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0510 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1307 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 363/500

Epoch 00363: val_loss did not improve from 0.02486
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0510 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1306 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 364/500

Epoch 00364: val_loss improved from 0.02486 to 0.02479, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0514 - val_loss: 0.0248 - val_mse: 0.0248 - val_mae: 0.1292 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 365/500

Epoch 00365: val_loss improved from 0.02479 to 0.02463, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0497 - val_loss: 0.0246 - val_mse: 0.0246 - val_mae: 0.1287 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 366/500

Epoch 00366: val_loss did not improve from 0.02463
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0527 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1297 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 367/500

Epoch 00367: val_loss did not improve from 0.02463
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0506 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1297 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 368/500

Epoch 00368: val_loss did not improve from 0.02463
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0522 - val_loss: 0.0247 - val_mse: 0.0247 - val_mae: 0.1291 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 369/500

Epoch 00369: val_loss did not improve from 0.02463
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0518 - val_loss: 0.0247 - val_mse: 0.0247 - val_mae: 0.1289 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 370/500

Epoch 00370: val_loss did not improve from 0.02463
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0536 - val_loss: 0.0246 - val_mse: 0.0246 - val_mae: 0.1289 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 371/500

Epoch 00371: val_loss improved from 0.02463 to 0.02450, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0509 - val_loss: 0.0245 - val_mse: 0.0245 - val_mae: 0.1284 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 372/500

Epoch 00372: val_loss improved from 0.02450 to 0.02412, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0507 - val_loss: 0.0241 - val_mse: 0.0241 - val_mae: 0.1271 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 373/500

Epoch 00373: val_loss improved from 0.02412 to 0.02408, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0503 - val_loss: 0.0241 - val_mse: 0.0241 - val_mae: 0.1270 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 374/500

Epoch 00374: val_loss did not improve from 0.02408
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0517 - val_loss: 0.0241 - val_mse: 0.0241 - val_mae: 0.1272 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 375/500

Epoch 00375: val_loss did not improve from 0.02408
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0528 - val_loss: 0.0242 - val_mse: 0.0242 - val_mae: 0.1274 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 376/500

Epoch 00376: val_loss improved from 0.02408 to 0.02405, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0504 - val_loss: 0.0241 - val_mse: 0.0241 - val_mae: 0.1270 - lr: 1.0000e-05 - 116ms/epoch - 7ms/step
Epoch 377/500

Epoch 00377: val_loss did not improve from 0.02405
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0515 - val_loss: 0.0241 - val_mse: 0.0241 - val_mae: 0.1271 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 378/500

Epoch 00378: val_loss did not improve from 0.02405
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0511 - val_loss: 0.0241 - val_mse: 0.0241 - val_mae: 0.1270 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 379/500

Epoch 00379: val_loss improved from 0.02405 to 0.02386, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0502 - val_loss: 0.0239 - val_mse: 0.0239 - val_mae: 0.1263 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 380/500

Epoch 00380: val_loss improved from 0.02386 to 0.02352, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0500 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1252 - lr: 1.0000e-05 - 122ms/epoch - 8ms/step
Epoch 381/500

Epoch 00381: val_loss did not improve from 0.02352
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0530 - val_loss: 0.0237 - val_mse: 0.0237 - val_mae: 0.1259 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 382/500

Epoch 00382: val_loss did not improve from 0.02352
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0528 - val_loss: 0.0239 - val_mse: 0.0239 - val_mae: 0.1265 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 383/500

Epoch 00383: val_loss did not improve from 0.02352
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0499 - val_loss: 0.0240 - val_mse: 0.0240 - val_mae: 0.1271 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 384/500

Epoch 00384: val_loss did not improve from 0.02352
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0511 - val_loss: 0.0241 - val_mse: 0.0241 - val_mae: 0.1274 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 385/500

Epoch 00385: val_loss did not improve from 0.02352
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0516 - val_loss: 0.0241 - val_mse: 0.0241 - val_mae: 0.1272 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 386/500

Epoch 00386: val_loss did not improve from 0.02352
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0509 - val_loss: 0.0242 - val_mse: 0.0242 - val_mae: 0.1275 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 387/500

Epoch 00387: val_loss did not improve from 0.02352
16/16 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0486 - val_loss: 0.0237 - val_mse: 0.0237 - val_mae: 0.1260 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 388/500

Epoch 00388: val_loss did not improve from 0.02352
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0497 - val_loss: 0.0236 - val_mse: 0.0236 - val_mae: 0.1256 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 389/500

Epoch 00389: val_loss improved from 0.02352 to 0.02352, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0494 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1254 - lr: 1.0000e-05 - 121ms/epoch - 8ms/step
Epoch 390/500

Epoch 00390: val_loss improved from 0.02352 to 0.02337, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0509 - val_loss: 0.0234 - val_mse: 0.0234 - val_mae: 0.1249 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 391/500

Epoch 00391: val_loss improved from 0.02337 to 0.02320, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0511 - val_loss: 0.0232 - val_mse: 0.0232 - val_mae: 0.1243 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 392/500

Epoch 00392: val_loss did not improve from 0.02320
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0500 - val_loss: 0.0233 - val_mse: 0.0233 - val_mae: 0.1246 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 393/500

Epoch 00393: val_loss improved from 0.02320 to 0.02318, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0513 - val_loss: 0.0232 - val_mse: 0.0232 - val_mae: 0.1243 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 394/500

Epoch 00394: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0510 - val_loss: 0.0232 - val_mse: 0.0232 - val_mae: 0.1244 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 395/500

Epoch 00395: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0505 - val_loss: 0.0232 - val_mse: 0.0232 - val_mae: 0.1244 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 396/500

Epoch 00396: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0513 - val_loss: 0.0233 - val_mse: 0.0233 - val_mae: 0.1246 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 397/500

Epoch 00397: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0520 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1255 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 398/500

Epoch 00398: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0515 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1256 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 399/500

Epoch 00399: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0503 - val_loss: 0.0237 - val_mse: 0.0237 - val_mae: 0.1260 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 400/500

Epoch 00400: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0519 - val_loss: 0.0237 - val_mse: 0.0237 - val_mae: 0.1263 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 401/500

Epoch 00401: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0493 - val_loss: 0.0236 - val_mse: 0.0236 - val_mae: 0.1259 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 402/500

Epoch 00402: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0507 - val_loss: 0.0234 - val_mse: 0.0234 - val_mae: 0.1253 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 403/500

Epoch 00403: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0511 - val_loss: 0.0233 - val_mse: 0.0233 - val_mae: 0.1248 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 404/500

Epoch 00404: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0517 - val_loss: 0.0237 - val_mse: 0.0237 - val_mae: 0.1263 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 405/500

Epoch 00405: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0493 - val_loss: 0.0239 - val_mse: 0.0239 - val_mae: 0.1269 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 406/500

Epoch 00406: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0514 - val_loss: 0.0237 - val_mse: 0.0237 - val_mae: 0.1262 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 407/500

Epoch 00407: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0514 - val_loss: 0.0236 - val_mse: 0.0236 - val_mae: 0.1260 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 408/500

Epoch 00408: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0496 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1255 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 409/500

Epoch 00409: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0497 - val_loss: 0.0237 - val_mse: 0.0237 - val_mae: 0.1263 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 410/500

Epoch 00410: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0530 - val_loss: 0.0238 - val_mse: 0.0238 - val_mae: 0.1267 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 411/500

Epoch 00411: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0510 - val_loss: 0.0239 - val_mse: 0.0239 - val_mae: 0.1269 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 412/500

Epoch 00412: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0511 - val_loss: 0.0236 - val_mse: 0.0236 - val_mae: 0.1258 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 413/500

Epoch 00413: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0501 - val_loss: 0.0234 - val_mse: 0.0234 - val_mae: 0.1254 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 414/500

Epoch 00414: val_loss did not improve from 0.02318
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0487 - val_loss: 0.0233 - val_mse: 0.0233 - val_mae: 0.1250 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 415/500

Epoch 00415: val_loss improved from 0.02318 to 0.02312, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0505 - val_loss: 0.0231 - val_mse: 0.0231 - val_mae: 0.1244 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 416/500

Epoch 00416: val_loss improved from 0.02312 to 0.02293, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0510 - val_loss: 0.0229 - val_mse: 0.0229 - val_mae: 0.1238 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 417/500

Epoch 00417: val_loss improved from 0.02293 to 0.02284, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0512 - val_loss: 0.0228 - val_mse: 0.0228 - val_mae: 0.1235 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 418/500

Epoch 00418: val_loss did not improve from 0.02284
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0510 - val_loss: 0.0230 - val_mse: 0.0230 - val_mae: 0.1241 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 419/500

Epoch 00419: val_loss did not improve from 0.02284
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0503 - val_loss: 0.0231 - val_mse: 0.0231 - val_mae: 0.1245 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 420/500

Epoch 00420: val_loss did not improve from 0.02284
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0500 - val_loss: 0.0229 - val_mse: 0.0229 - val_mae: 0.1239 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 421/500

Epoch 00421: val_loss improved from 0.02284 to 0.02278, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0482 - val_loss: 0.0228 - val_mse: 0.0228 - val_mae: 0.1234 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 422/500

Epoch 00422: val_loss improved from 0.02278 to 0.02269, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0514 - val_loss: 0.0227 - val_mse: 0.0227 - val_mae: 0.1231 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 423/500

Epoch 00423: val_loss did not improve from 0.02269
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0490 - val_loss: 0.0228 - val_mse: 0.0228 - val_mae: 0.1235 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 424/500

Epoch 00424: val_loss improved from 0.02269 to 0.02268, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0491 - val_loss: 0.0227 - val_mse: 0.0227 - val_mae: 0.1231 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 425/500

Epoch 00425: val_loss improved from 0.02268 to 0.02262, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0497 - val_loss: 0.0226 - val_mse: 0.0226 - val_mae: 0.1228 - lr: 1.0000e-05 - 119ms/epoch - 7ms/step
Epoch 426/500

Epoch 00426: val_loss did not improve from 0.02262
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0526 - val_loss: 0.0226 - val_mse: 0.0226 - val_mae: 0.1229 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 427/500

Epoch 00427: val_loss did not improve from 0.02262
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0503 - val_loss: 0.0227 - val_mse: 0.0227 - val_mae: 0.1231 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 428/500

Epoch 00428: val_loss improved from 0.02262 to 0.02261, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0498 - val_loss: 0.0226 - val_mse: 0.0226 - val_mae: 0.1229 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 429/500

Epoch 00429: val_loss improved from 0.02261 to 0.02252, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0489 - val_loss: 0.0225 - val_mse: 0.0225 - val_mae: 0.1226 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 430/500

Epoch 00430: val_loss did not improve from 0.02252
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0506 - val_loss: 0.0227 - val_mse: 0.0227 - val_mae: 0.1231 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 431/500

Epoch 00431: val_loss did not improve from 0.02252
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0501 - val_loss: 0.0229 - val_mse: 0.0229 - val_mae: 0.1240 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 432/500

Epoch 00432: val_loss did not improve from 0.02252
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0491 - val_loss: 0.0230 - val_mse: 0.0230 - val_mae: 0.1241 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 433/500

Epoch 00433: val_loss did not improve from 0.02252
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0505 - val_loss: 0.0228 - val_mse: 0.0228 - val_mae: 0.1237 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 434/500

Epoch 00434: val_loss did not improve from 0.02252
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0501 - val_loss: 0.0226 - val_mse: 0.0226 - val_mae: 0.1231 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 435/500

Epoch 00435: val_loss improved from 0.02252 to 0.02229, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0496 - val_loss: 0.0223 - val_mse: 0.0223 - val_mae: 0.1219 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 436/500

Epoch 00436: val_loss improved from 0.02229 to 0.02221, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0516 - val_loss: 0.0222 - val_mse: 0.0222 - val_mae: 0.1216 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 437/500

Epoch 00437: val_loss did not improve from 0.02221
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0509 - val_loss: 0.0225 - val_mse: 0.0225 - val_mae: 0.1228 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 438/500

Epoch 00438: val_loss did not improve from 0.02221
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0493 - val_loss: 0.0225 - val_mse: 0.0225 - val_mae: 0.1225 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 439/500

Epoch 00439: val_loss did not improve from 0.02221
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0518 - val_loss: 0.0223 - val_mse: 0.0223 - val_mae: 0.1219 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 440/500

Epoch 00440: val_loss improved from 0.02221 to 0.02216, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0480 - val_loss: 0.0222 - val_mse: 0.0222 - val_mae: 0.1215 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 441/500

Epoch 00441: val_loss improved from 0.02216 to 0.02199, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0475 - val_loss: 0.0220 - val_mse: 0.0220 - val_mae: 0.1209 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 442/500

Epoch 00442: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0511 - val_loss: 0.0221 - val_mse: 0.0221 - val_mae: 0.1213 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 443/500

Epoch 00443: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0520 - val_loss: 0.0223 - val_mse: 0.0223 - val_mae: 0.1222 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 444/500

Epoch 00444: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0485 - val_loss: 0.0227 - val_mse: 0.0227 - val_mae: 0.1234 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 445/500

Epoch 00445: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0489 - val_loss: 0.0229 - val_mse: 0.0229 - val_mae: 0.1242 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 446/500

Epoch 00446: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0489 - val_loss: 0.0229 - val_mse: 0.0229 - val_mae: 0.1242 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 447/500

Epoch 00447: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0473 - val_loss: 0.0227 - val_mse: 0.0227 - val_mae: 0.1235 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 448/500

Epoch 00448: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0503 - val_loss: 0.0225 - val_mse: 0.0225 - val_mae: 0.1228 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 449/500

Epoch 00449: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0505 - val_loss: 0.0225 - val_mse: 0.0225 - val_mae: 0.1227 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 450/500

Epoch 00450: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0525 - val_loss: 0.0227 - val_mse: 0.0227 - val_mae: 0.1237 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 451/500

Epoch 00451: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0511 - val_loss: 0.0227 - val_mse: 0.0227 - val_mae: 0.1237 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 452/500

Epoch 00452: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0488 - val_loss: 0.0226 - val_mse: 0.0226 - val_mae: 0.1233 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 453/500

Epoch 00453: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0478 - val_loss: 0.0224 - val_mse: 0.0224 - val_mae: 0.1226 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 454/500

Epoch 00454: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0496 - val_loss: 0.0223 - val_mse: 0.0223 - val_mae: 0.1221 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 455/500

Epoch 00455: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0500 - val_loss: 0.0222 - val_mse: 0.0222 - val_mae: 0.1219 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 456/500

Epoch 00456: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0486 - val_loss: 0.0223 - val_mse: 0.0223 - val_mae: 0.1222 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 457/500

Epoch 00457: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0503 - val_loss: 0.0222 - val_mse: 0.0222 - val_mae: 0.1221 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 458/500

Epoch 00458: val_loss did not improve from 0.02199
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0511 - val_loss: 0.0220 - val_mse: 0.0220 - val_mae: 0.1213 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 459/500

Epoch 00459: val_loss improved from 0.02199 to 0.02181, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0485 - val_loss: 0.0218 - val_mse: 0.0218 - val_mae: 0.1206 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 460/500

Epoch 00460: val_loss did not improve from 0.02181
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0492 - val_loss: 0.0218 - val_mse: 0.0218 - val_mae: 0.1207 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 461/500

Epoch 00461: val_loss did not improve from 0.02181
16/16 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0475 - val_loss: 0.0219 - val_mse: 0.0219 - val_mae: 0.1209 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 462/500

Epoch 00462: val_loss did not improve from 0.02181
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0512 - val_loss: 0.0219 - val_mse: 0.0219 - val_mae: 0.1209 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 463/500

Epoch 00463: val_loss did not improve from 0.02181
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0505 - val_loss: 0.0219 - val_mse: 0.0219 - val_mae: 0.1210 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 464/500

Epoch 00464: val_loss did not improve from 0.02181
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0490 - val_loss: 0.0219 - val_mse: 0.0219 - val_mae: 0.1209 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 465/500

Epoch 00465: val_loss did not improve from 0.02181
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0495 - val_loss: 0.0219 - val_mse: 0.0219 - val_mae: 0.1209 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 466/500

Epoch 00466: val_loss did not improve from 0.02181
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0505 - val_loss: 0.0219 - val_mse: 0.0219 - val_mae: 0.1211 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 467/500

Epoch 00467: val_loss did not improve from 0.02181
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0510 - val_loss: 0.0219 - val_mse: 0.0219 - val_mae: 0.1209 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 468/500

Epoch 00468: val_loss improved from 0.02181 to 0.02172, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0492 - val_loss: 0.0217 - val_mse: 0.0217 - val_mae: 0.1203 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 469/500

Epoch 00469: val_loss did not improve from 0.02172
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0487 - val_loss: 0.0217 - val_mse: 0.0217 - val_mae: 0.1204 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 470/500

Epoch 00470: val_loss improved from 0.02172 to 0.02164, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0486 - val_loss: 0.0216 - val_mse: 0.0216 - val_mae: 0.1201 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 471/500

Epoch 00471: val_loss improved from 0.02164 to 0.02155, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0488 - val_loss: 0.0215 - val_mse: 0.0215 - val_mae: 0.1198 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 472/500

Epoch 00472: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0482 - val_loss: 0.0217 - val_mse: 0.0217 - val_mae: 0.1202 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 473/500

Epoch 00473: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0480 - val_loss: 0.0219 - val_mse: 0.0219 - val_mae: 0.1209 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 474/500

Epoch 00474: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0495 - val_loss: 0.0220 - val_mse: 0.0220 - val_mae: 0.1215 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 475/500

Epoch 00475: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0516 - val_loss: 0.0219 - val_mse: 0.0219 - val_mae: 0.1210 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 476/500

Epoch 00476: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0506 - val_loss: 0.0216 - val_mse: 0.0216 - val_mae: 0.1201 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 477/500

Epoch 00477: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0495 - val_loss: 0.0217 - val_mse: 0.0217 - val_mae: 0.1203 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 478/500

Epoch 00478: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0481 - val_loss: 0.0218 - val_mse: 0.0218 - val_mae: 0.1207 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 479/500

Epoch 00479: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0471 - val_loss: 0.0218 - val_mse: 0.0218 - val_mae: 0.1209 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 480/500

Epoch 00480: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0487 - val_loss: 0.0217 - val_mse: 0.0217 - val_mae: 0.1206 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 481/500

Epoch 00481: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0515 - val_loss: 0.0216 - val_mse: 0.0216 - val_mae: 0.1203 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 482/500

Epoch 00482: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0502 - val_loss: 0.0217 - val_mse: 0.0217 - val_mae: 0.1205 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 483/500

Epoch 00483: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0485 - val_loss: 0.0218 - val_mse: 0.0218 - val_mae: 0.1208 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 484/500

Epoch 00484: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0495 - val_loss: 0.0219 - val_mse: 0.0219 - val_mae: 0.1213 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 485/500

Epoch 00485: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0460 - val_loss: 0.0218 - val_mse: 0.0218 - val_mae: 0.1210 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 486/500

Epoch 00486: val_loss did not improve from 0.02155
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0493 - val_loss: 0.0217 - val_mse: 0.0217 - val_mae: 0.1206 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 487/500

Epoch 00487: val_loss improved from 0.02155 to 0.02147, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0501 - val_loss: 0.0215 - val_mse: 0.0215 - val_mae: 0.1197 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 488/500

Epoch 00488: val_loss improved from 0.02147 to 0.02127, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0503 - val_loss: 0.0213 - val_mse: 0.0213 - val_mae: 0.1190 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 489/500

Epoch 00489: val_loss did not improve from 0.02127
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0481 - val_loss: 0.0213 - val_mse: 0.0213 - val_mae: 0.1191 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 490/500

Epoch 00490: val_loss did not improve from 0.02127
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0482 - val_loss: 0.0214 - val_mse: 0.0214 - val_mae: 0.1197 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 491/500

Epoch 00491: val_loss did not improve from 0.02127
16/16 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0475 - val_loss: 0.0216 - val_mse: 0.0216 - val_mae: 0.1202 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 492/500

Epoch 00492: val_loss did not improve from 0.02127
16/16 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0476 - val_loss: 0.0214 - val_mse: 0.0214 - val_mae: 0.1197 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 493/500

Epoch 00493: val_loss did not improve from 0.02127
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0506 - val_loss: 0.0214 - val_mse: 0.0214 - val_mae: 0.1196 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 494/500

Epoch 00494: val_loss did not improve from 0.02127
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0516 - val_loss: 0.0216 - val_mse: 0.0216 - val_mae: 0.1202 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 495/500

Epoch 00495: val_loss did not improve from 0.02127
16/16 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0484 - val_loss: 0.0217 - val_mse: 0.0217 - val_mae: 0.1207 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 496/500

Epoch 00496: val_loss did not improve from 0.02127
16/16 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0484 - val_loss: 0.0216 - val_mse: 0.0216 - val_mae: 0.1205 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 497/500

Epoch 00497: val_loss did not improve from 0.02127
16/16 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0496 - val_loss: 0.0214 - val_mse: 0.0214 - val_mae: 0.1198 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 498/500

Epoch 00498: val_loss improved from 0.02127 to 0.02122, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0491 - val_loss: 0.0212 - val_mse: 0.0212 - val_mae: 0.1190 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 499/500

Epoch 00499: val_loss did not improve from 0.02122
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0516 - val_loss: 0.0213 - val_mse: 0.0213 - val_mae: 0.1193 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 500/500

Epoch 00500: val_loss improved from 0.02122 to 0.02099, saving model to LSTM3.h5
16/16 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0496 - val_loss: 0.0210 - val_mse: 0.0210 - val_mae: 0.1183 - lr: 1.0000e-05 - 122ms/epoch - 8ms/step

SMA
Prediction vs Close:		51.49% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 32.725767438505336 
RMSE:	 5.7206439706125165 
MAPE:	 4.798603095387009

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 143.9522591181831 
RMSE:	 11.998010631691534 
MAPE:	 10.07848404711658
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.40 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4264.089, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3793.930, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.26 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3564.923, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3427.258, Time=0.08 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.24 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.45 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3429.258, Time=0.19 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.750 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1709.629
Date:                Sun, 12 Dec 2021   AIC                           3427.258
Time:                        15:01:30   BIC                           3446.021
Sample:                             0   HQIC                          3434.464
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1981      0.003   -389.386      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.699      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.737      0.000      -0.410      -0.387
sigma2         4.0860      0.019    215.311      0.000       4.049       4.123
===================================================================================
Ljung-Box (L1) (Q):                  14.57   Jarque-Bera (JB):           2460901.70
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.75
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.02131, saving model to LSTM3.h5
17/17 - 2s - loss: 0.8890 - mse: 0.8890 - mae: 0.7526 - val_loss: 0.0213 - val_mse: 0.0213 - val_mae: 0.1190 - lr: 0.0010 - 2s/epoch - 127ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.02131 to 0.02058, saving model to LSTM3.h5
17/17 - 0s - loss: 0.1482 - mse: 0.1482 - mae: 0.3315 - val_loss: 0.0206 - val_mse: 0.0206 - val_mae: 0.1164 - lr: 0.0010 - 99ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0742 - mse: 0.0742 - mae: 0.2245 - val_loss: 0.0353 - val_mse: 0.0353 - val_mae: 0.1535 - lr: 0.0010 - 90ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0478 - mse: 0.0478 - mae: 0.1730 - val_loss: 0.0454 - val_mse: 0.0454 - val_mae: 0.1777 - lr: 0.0010 - 90ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0391 - mse: 0.0391 - mae: 0.1575 - val_loss: 0.0570 - val_mse: 0.0570 - val_mae: 0.2042 - lr: 0.0010 - 87ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0314 - mse: 0.0314 - mae: 0.1422 - val_loss: 0.0658 - val_mse: 0.0658 - val_mae: 0.2229 - lr: 0.0010 - 84ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00007: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0287 - mse: 0.0287 - mae: 0.1361 - val_loss: 0.0708 - val_mse: 0.0708 - val_mae: 0.2332 - lr: 0.0010 - 88ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0265 - mse: 0.0265 - mae: 0.1282 - val_loss: 0.0709 - val_mse: 0.0709 - val_mae: 0.2336 - lr: 1.0000e-04 - 107ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0251 - mse: 0.0251 - mae: 0.1272 - val_loss: 0.0713 - val_mse: 0.0713 - val_mae: 0.2345 - lr: 1.0000e-04 - 117ms/epoch - 7ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0249 - mse: 0.0249 - mae: 0.1266 - val_loss: 0.0718 - val_mse: 0.0718 - val_mae: 0.2355 - lr: 1.0000e-04 - 111ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0238 - mse: 0.0238 - mae: 0.1242 - val_loss: 0.0720 - val_mse: 0.0720 - val_mae: 0.2359 - lr: 1.0000e-04 - 103ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00012: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0255 - mse: 0.0255 - mae: 0.1280 - val_loss: 0.0724 - val_mse: 0.0724 - val_mae: 0.2369 - lr: 1.0000e-04 - 106ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0245 - mse: 0.0245 - mae: 0.1244 - val_loss: 0.0725 - val_mse: 0.0725 - val_mae: 0.2370 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0245 - mse: 0.0245 - mae: 0.1249 - val_loss: 0.0725 - val_mse: 0.0725 - val_mae: 0.2370 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0255 - mse: 0.0255 - mae: 0.1276 - val_loss: 0.0725 - val_mse: 0.0725 - val_mae: 0.2371 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0246 - mse: 0.0246 - mae: 0.1245 - val_loss: 0.0725 - val_mse: 0.0725 - val_mae: 0.2371 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00017: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0242 - mse: 0.0242 - mae: 0.1238 - val_loss: 0.0726 - val_mse: 0.0726 - val_mae: 0.2372 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0242 - mse: 0.0242 - mae: 0.1228 - val_loss: 0.0726 - val_mse: 0.0726 - val_mae: 0.2372 - lr: 1.0000e-05 - 92ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0241 - mse: 0.0241 - mae: 0.1229 - val_loss: 0.0726 - val_mse: 0.0726 - val_mae: 0.2372 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0248 - mse: 0.0248 - mae: 0.1262 - val_loss: 0.0726 - val_mse: 0.0726 - val_mae: 0.2374 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0248 - mse: 0.0248 - mae: 0.1246 - val_loss: 0.0727 - val_mse: 0.0727 - val_mae: 0.2375 - lr: 1.0000e-05 - 92ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0255 - mse: 0.0255 - mae: 0.1286 - val_loss: 0.0727 - val_mse: 0.0727 - val_mae: 0.2376 - lr: 1.0000e-05 - 89ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0242 - mse: 0.0242 - mae: 0.1249 - val_loss: 0.0728 - val_mse: 0.0728 - val_mae: 0.2376 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0249 - mse: 0.0249 - mae: 0.1279 - val_loss: 0.0728 - val_mse: 0.0728 - val_mae: 0.2377 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0242 - mse: 0.0242 - mae: 0.1231 - val_loss: 0.0729 - val_mse: 0.0729 - val_mae: 0.2378 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0234 - mse: 0.0234 - mae: 0.1214 - val_loss: 0.0729 - val_mse: 0.0729 - val_mae: 0.2380 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0228 - mse: 0.0228 - mae: 0.1210 - val_loss: 0.0730 - val_mse: 0.0730 - val_mae: 0.2382 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0221 - mse: 0.0221 - mae: 0.1218 - val_loss: 0.0731 - val_mse: 0.0731 - val_mae: 0.2383 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0245 - mse: 0.0245 - mae: 0.1267 - val_loss: 0.0731 - val_mse: 0.0731 - val_mae: 0.2383 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0262 - mse: 0.0262 - mae: 0.1286 - val_loss: 0.0731 - val_mse: 0.0731 - val_mae: 0.2384 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0245 - mse: 0.0245 - mae: 0.1259 - val_loss: 0.0731 - val_mse: 0.0731 - val_mae: 0.2384 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0248 - mse: 0.0248 - mae: 0.1273 - val_loss: 0.0731 - val_mse: 0.0731 - val_mae: 0.2383 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0249 - mse: 0.0249 - mae: 0.1275 - val_loss: 0.0731 - val_mse: 0.0731 - val_mae: 0.2384 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0223 - mse: 0.0223 - mae: 0.1180 - val_loss: 0.0731 - val_mse: 0.0731 - val_mae: 0.2385 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0229 - mse: 0.0229 - mae: 0.1227 - val_loss: 0.0732 - val_mse: 0.0732 - val_mae: 0.2387 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0252 - mse: 0.0252 - mae: 0.1272 - val_loss: 0.0733 - val_mse: 0.0733 - val_mae: 0.2388 - lr: 1.0000e-05 - 93ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0254 - mse: 0.0254 - mae: 0.1276 - val_loss: 0.0733 - val_mse: 0.0733 - val_mae: 0.2389 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0230 - mse: 0.0230 - mae: 0.1210 - val_loss: 0.0735 - val_mse: 0.0735 - val_mae: 0.2392 - lr: 1.0000e-05 - 108ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0245 - mse: 0.0245 - mae: 0.1249 - val_loss: 0.0735 - val_mse: 0.0735 - val_mae: 0.2392 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0219 - mse: 0.0219 - mae: 0.1178 - val_loss: 0.0735 - val_mse: 0.0735 - val_mae: 0.2394 - lr: 1.0000e-05 - 90ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0240 - mse: 0.0240 - mae: 0.1242 - val_loss: 0.0736 - val_mse: 0.0736 - val_mae: 0.2395 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0239 - mse: 0.0239 - mae: 0.1250 - val_loss: 0.0736 - val_mse: 0.0736 - val_mae: 0.2396 - lr: 1.0000e-05 - 90ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0243 - mse: 0.0243 - mae: 0.1244 - val_loss: 0.0736 - val_mse: 0.0736 - val_mae: 0.2395 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0228 - mse: 0.0228 - mae: 0.1221 - val_loss: 0.0736 - val_mse: 0.0736 - val_mae: 0.2395 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0219 - mse: 0.0219 - mae: 0.1177 - val_loss: 0.0736 - val_mse: 0.0736 - val_mae: 0.2396 - lr: 1.0000e-05 - 92ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0217 - mse: 0.0217 - mae: 0.1162 - val_loss: 0.0737 - val_mse: 0.0737 - val_mae: 0.2397 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0265 - mse: 0.0265 - mae: 0.1279 - val_loss: 0.0736 - val_mse: 0.0736 - val_mae: 0.2396 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0236 - mse: 0.0236 - mae: 0.1218 - val_loss: 0.0736 - val_mse: 0.0736 - val_mae: 0.2396 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0226 - mse: 0.0226 - mae: 0.1212 - val_loss: 0.0737 - val_mse: 0.0737 - val_mae: 0.2397 - lr: 1.0000e-05 - 90ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0227 - mse: 0.0227 - mae: 0.1186 - val_loss: 0.0737 - val_mse: 0.0737 - val_mae: 0.2397 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0237 - mse: 0.0237 - mae: 0.1222 - val_loss: 0.0737 - val_mse: 0.0737 - val_mae: 0.2398 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.02058
17/17 - 0s - loss: 0.0208 - mse: 0.0208 - mae: 0.1157 - val_loss: 0.0737 - val_mse: 0.0737 - val_mae: 0.2399 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 00052: early stopping

SMA
Prediction vs Close:		51.49% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 32.725767438505336 
RMSE:	 5.7206439706125165 
MAPE:	 4.798603095387009

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 143.9522591181831 
RMSE:	 11.998010631691534 
MAPE:	 10.07848404711658

WMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 24.586224407987817 
RMSE:	 4.958449798877449 
MAPE:	 3.970226889097132
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.42 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4436.126, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3965.317, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.38 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3736.589, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3598.951, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.91 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.90 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3600.951, Time=0.21 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.040 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1795.475
Date:                Sun, 12 Dec 2021   AIC                           3598.951
Time:                        15:02:45   BIC                           3617.714
Sample:                             0   HQIC                          3606.157
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1983      0.003   -389.581      0.000      -1.204      -1.192
ar.L2         -0.8973      0.006   -139.732      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.649      0.000      -0.410      -0.387
sigma2         5.0573      0.023    215.292      0.000       5.011       5.103
===================================================================================
Ljung-Box (L1) (Q):                  14.41   Jarque-Bera (JB):           2460553.80
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.89
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.74
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.14531, saving model to LSTM3.h5
10/10 - 3s - loss: 0.4588 - mse: 0.4588 - mae: 0.5822 - val_loss: 0.1453 - val_mse: 0.1453 - val_mae: 0.3471 - lr: 0.0010 - 3s/epoch - 252ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.14531 to 0.06661, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0766 - mse: 0.0766 - mae: 0.2246 - val_loss: 0.0666 - val_mse: 0.0666 - val_mae: 0.2219 - lr: 0.0010 - 86ms/epoch - 9ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.06661 to 0.03347, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0677 - mse: 0.0677 - mae: 0.2234 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1513 - lr: 0.0010 - 90ms/epoch - 9ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.03347 to 0.01798, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0283 - mse: 0.0283 - mae: 0.1346 - val_loss: 0.0180 - val_mse: 0.0180 - val_mae: 0.1095 - lr: 0.0010 - 76ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.01798 to 0.01389, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0252 - mse: 0.0252 - mae: 0.1227 - val_loss: 0.0139 - val_mse: 0.0139 - val_mae: 0.0965 - lr: 0.0010 - 77ms/epoch - 8ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.01389 to 0.01325, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0227 - mse: 0.0227 - mae: 0.1170 - val_loss: 0.0132 - val_mse: 0.0132 - val_mae: 0.0939 - lr: 0.0010 - 90ms/epoch - 9ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.01325
10/10 - 0s - loss: 0.0199 - mse: 0.0199 - mae: 0.1116 - val_loss: 0.0133 - val_mse: 0.0133 - val_mae: 0.0931 - lr: 0.0010 - 74ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.01325 to 0.01313, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0160 - mse: 0.0160 - mae: 0.1009 - val_loss: 0.0131 - val_mse: 0.0131 - val_mae: 0.0922 - lr: 0.0010 - 72ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.01313 to 0.01294, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0150 - mse: 0.0150 - mae: 0.0960 - val_loss: 0.0129 - val_mse: 0.0129 - val_mae: 0.0916 - lr: 0.0010 - 85ms/epoch - 8ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.01294 to 0.01274, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0132 - mse: 0.0132 - mae: 0.0896 - val_loss: 0.0127 - val_mse: 0.0127 - val_mae: 0.0911 - lr: 0.0010 - 84ms/epoch - 8ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.01274 to 0.01251, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0128 - mse: 0.0128 - mae: 0.0880 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0907 - lr: 0.0010 - 82ms/epoch - 8ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.01251
10/10 - 0s - loss: 0.0113 - mse: 0.0113 - mae: 0.0834 - val_loss: 0.0127 - val_mse: 0.0127 - val_mae: 0.0921 - lr: 0.0010 - 82ms/epoch - 8ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.01251 to 0.01239, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0112 - mse: 0.0112 - mae: 0.0834 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0910 - lr: 0.0010 - 86ms/epoch - 9ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.01239 to 0.01209, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0103 - mse: 0.0103 - mae: 0.0797 - val_loss: 0.0121 - val_mse: 0.0121 - val_mae: 0.0898 - lr: 0.0010 - 86ms/epoch - 9ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.01209
10/10 - 0s - loss: 0.0097 - mse: 0.0097 - mae: 0.0784 - val_loss: 0.0121 - val_mse: 0.0121 - val_mae: 0.0904 - lr: 0.0010 - 69ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.01209
10/10 - 0s - loss: 0.0093 - mse: 0.0093 - mae: 0.0765 - val_loss: 0.0121 - val_mse: 0.0121 - val_mae: 0.0905 - lr: 0.0010 - 58ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.01209 to 0.01191, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0091 - mse: 0.0091 - mae: 0.0755 - val_loss: 0.0119 - val_mse: 0.0119 - val_mae: 0.0895 - lr: 0.0010 - 96ms/epoch - 10ms/step
Epoch 18/500

Epoch 00018: val_loss improved from 0.01191 to 0.01123, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0080 - mse: 0.0080 - mae: 0.0719 - val_loss: 0.0112 - val_mse: 0.0112 - val_mae: 0.0859 - lr: 0.0010 - 74ms/epoch - 7ms/step
Epoch 19/500

Epoch 00019: val_loss improved from 0.01123 to 0.01102, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0685 - val_loss: 0.0110 - val_mse: 0.0110 - val_mae: 0.0853 - lr: 0.0010 - 76ms/epoch - 8ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.01102 to 0.01081, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0080 - mse: 0.0080 - mae: 0.0697 - val_loss: 0.0108 - val_mse: 0.0108 - val_mae: 0.0845 - lr: 0.0010 - 76ms/epoch - 8ms/step
Epoch 21/500

Epoch 00021: val_loss improved from 0.01081 to 0.01046, saving model to LSTM3.h5
10/10 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0710 - val_loss: 0.0105 - val_mse: 0.0105 - val_mae: 0.0826 - lr: 0.0010 - 88ms/epoch - 9ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0675 - val_loss: 0.0109 - val_mse: 0.0109 - val_mae: 0.0860 - lr: 0.0010 - 68ms/epoch - 7ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0681 - val_loss: 0.0114 - val_mse: 0.0114 - val_mae: 0.0880 - lr: 0.0010 - 64ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0666 - val_loss: 0.0131 - val_mse: 0.0131 - val_mae: 0.0949 - lr: 0.0010 - 58ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0656 - val_loss: 0.0126 - val_mse: 0.0126 - val_mae: 0.0934 - lr: 0.0010 - 73ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00026: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0623 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0930 - lr: 0.0010 - 61ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0628 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0925 - lr: 1.0000e-04 - 65ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0619 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0927 - lr: 1.0000e-04 - 64ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0602 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0931 - lr: 1.0000e-04 - 70ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0609 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0932 - lr: 1.0000e-04 - 70ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00031: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0638 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0928 - lr: 1.0000e-04 - 73ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0611 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0927 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0618 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0928 - lr: 1.0000e-05 - 59ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0616 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0929 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0603 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0930 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00036: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0654 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0930 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0669 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0930 - lr: 1.0000e-05 - 75ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0633 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0931 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0644 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0931 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0620 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0930 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0644 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0929 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0629 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0930 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0598 - val_loss: 0.0125 - val_mse: 0.0125 - val_mae: 0.0929 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0631 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0928 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0625 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0927 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0637 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0927 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0606 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0927 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0608 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0927 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0621 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0927 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0614 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0925 - lr: 1.0000e-05 - 80ms/epoch - 8ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0621 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0924 - lr: 1.0000e-05 - 86ms/epoch - 9ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0618 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0923 - lr: 1.0000e-05 - 82ms/epoch - 8ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0576 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0923 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0603 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0923 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0623 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0922 - lr: 1.0000e-05 - 79ms/epoch - 8ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0652 - val_loss: 0.0122 - val_mse: 0.0122 - val_mae: 0.0921 - lr: 1.0000e-05 - 77ms/epoch - 8ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0620 - val_loss: 0.0122 - val_mse: 0.0122 - val_mae: 0.0921 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0605 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0922 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0616 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0923 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0647 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0922 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0600 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0922 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0646 - val_loss: 0.0122 - val_mse: 0.0122 - val_mae: 0.0921 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0624 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0921 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0625 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0922 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0606 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0923 - lr: 1.0000e-05 - 75ms/epoch - 7ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0623 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0924 - lr: 1.0000e-05 - 65ms/epoch - 6ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0594 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0925 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0612 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0925 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0608 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0926 - lr: 1.0000e-05 - 79ms/epoch - 8ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0601 - val_loss: 0.0124 - val_mse: 0.0124 - val_mae: 0.0926 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.01046
10/10 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0612 - val_loss: 0.0123 - val_mse: 0.0123 - val_mae: 0.0925 - lr: 1.0000e-05 - 79ms/epoch - 8ms/step
Epoch 00071: early stopping

SMA
Prediction vs Close:		51.49% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 32.725767438505336 
RMSE:	 5.7206439706125165 
MAPE:	 4.798603095387009

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 143.9522591181831 
RMSE:	 11.998010631691534 
MAPE:	 10.07848404711658

WMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 24.586224407987817 
RMSE:	 4.958449798877449 
MAPE:	 3.970226889097132

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	51.49% Accuracy
MSE:	 207.2547601932076 
RMSE:	 14.3963453762824 
MAPE:	 12.894635987621164
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.36 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4190.464, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3724.371, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.28 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3494.154, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3357.435, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.18 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.70 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3359.435, Time=0.24 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.989 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1674.717
Date:                Sun, 12 Dec 2021   AIC                           3357.435
Time:                        15:04:02   BIC                           3376.198
Sample:                             0   HQIC                          3364.641
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1955      0.003   -381.246      0.000      -1.202      -1.189
ar.L2         -0.8964      0.007   -135.835      0.000      -0.909      -0.883
ar.L3         -0.3971      0.006    -67.229      0.000      -0.409      -0.385
sigma2         3.7466      0.018    211.623      0.000       3.712       3.781
===================================================================================
Ljung-Box (L1) (Q):                  14.20   Jarque-Bera (JB):           2338363.32
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             3.76
Prob(H) (two-sided):                  0.00   Kurtosis:                       266.93
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.52870, saving model to LSTM3.h5
45/45 - 2s - loss: 0.1434 - mse: 0.1434 - mae: 0.3013 - val_loss: 0.5287 - val_mse: 0.5287 - val_mae: 0.6882 - lr: 0.0010 - 2s/epoch - 49ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.52870 to 0.22252, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0645 - mse: 0.0645 - mae: 0.2074 - val_loss: 0.2225 - val_mse: 0.2225 - val_mae: 0.4296 - lr: 0.0010 - 216ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.22252 to 0.11434, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0430 - mse: 0.0430 - mae: 0.1667 - val_loss: 0.1143 - val_mse: 0.1143 - val_mae: 0.2943 - lr: 0.0010 - 240ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.11434 to 0.07710, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0251 - mse: 0.0251 - mae: 0.1281 - val_loss: 0.0771 - val_mse: 0.0771 - val_mae: 0.2329 - lr: 0.0010 - 220ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.07710 to 0.05932, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0175 - mse: 0.0175 - mae: 0.1066 - val_loss: 0.0593 - val_mse: 0.0593 - val_mae: 0.1992 - lr: 0.0010 - 237ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.05932 to 0.05014, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0134 - mse: 0.0134 - mae: 0.0935 - val_loss: 0.0501 - val_mse: 0.0501 - val_mae: 0.1808 - lr: 0.0010 - 227ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.05014
45/45 - 0s - loss: 0.0114 - mse: 0.0114 - mae: 0.0837 - val_loss: 0.0542 - val_mse: 0.0542 - val_mae: 0.1922 - lr: 0.0010 - 251ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.05014
45/45 - 0s - loss: 0.0105 - mse: 0.0105 - mae: 0.0823 - val_loss: 0.0536 - val_mse: 0.0536 - val_mae: 0.1921 - lr: 0.0010 - 189ms/epoch - 4ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.05014 to 0.04707, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0085 - mse: 0.0085 - mae: 0.0739 - val_loss: 0.0471 - val_mse: 0.0471 - val_mae: 0.1781 - lr: 0.0010 - 213ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04707
45/45 - 0s - loss: 0.0090 - mse: 0.0090 - mae: 0.0764 - val_loss: 0.0554 - val_mse: 0.0554 - val_mae: 0.1979 - lr: 0.0010 - 187ms/epoch - 4ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.04707 to 0.04541, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0707 - val_loss: 0.0454 - val_mse: 0.0454 - val_mae: 0.1760 - lr: 0.0010 - 255ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04541
45/45 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0721 - val_loss: 0.0535 - val_mse: 0.0535 - val_mae: 0.1954 - lr: 0.0010 - 220ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.04541 to 0.04341, saving model to LSTM3.h5
45/45 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0644 - val_loss: 0.0434 - val_mse: 0.0434 - val_mae: 0.1726 - lr: 0.0010 - 245ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0645 - val_loss: 0.0495 - val_mse: 0.0495 - val_mae: 0.1879 - lr: 0.0010 - 178ms/epoch - 4ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0594 - val_loss: 0.0508 - val_mse: 0.0508 - val_mae: 0.1916 - lr: 0.0010 - 241ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0615 - val_loss: 0.0451 - val_mse: 0.0451 - val_mae: 0.1783 - lr: 0.0010 - 243ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0546 - val_loss: 0.0724 - val_mse: 0.0724 - val_mae: 0.2376 - lr: 0.0010 - 264ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00018: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0561 - val_loss: 0.0595 - val_mse: 0.0595 - val_mae: 0.2114 - lr: 0.0010 - 229ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0500 - val_loss: 0.0594 - val_mse: 0.0594 - val_mae: 0.2112 - lr: 1.0000e-04 - 224ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0508 - val_loss: 0.0593 - val_mse: 0.0593 - val_mae: 0.2112 - lr: 1.0000e-04 - 232ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0512 - val_loss: 0.0597 - val_mse: 0.0597 - val_mae: 0.2120 - lr: 1.0000e-04 - 218ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0519 - val_loss: 0.0601 - val_mse: 0.0601 - val_mae: 0.2130 - lr: 1.0000e-04 - 265ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00023: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0519 - val_loss: 0.0597 - val_mse: 0.0597 - val_mae: 0.2124 - lr: 1.0000e-04 - 231ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0495 - val_loss: 0.0599 - val_mse: 0.0599 - val_mae: 0.2128 - lr: 1.0000e-05 - 222ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0479 - val_loss: 0.0598 - val_mse: 0.0598 - val_mae: 0.2126 - lr: 1.0000e-05 - 209ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0482 - val_loss: 0.0599 - val_mse: 0.0599 - val_mae: 0.2127 - lr: 1.0000e-05 - 213ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0492 - val_loss: 0.0598 - val_mse: 0.0598 - val_mae: 0.2125 - lr: 1.0000e-05 - 189ms/epoch - 4ms/step
Epoch 28/500

Epoch 00028: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00028: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0509 - val_loss: 0.0597 - val_mse: 0.0597 - val_mae: 0.2123 - lr: 1.0000e-05 - 273ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0496 - val_loss: 0.0598 - val_mse: 0.0598 - val_mae: 0.2126 - lr: 1.0000e-05 - 185ms/epoch - 4ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0459 - val_loss: 0.0598 - val_mse: 0.0598 - val_mae: 0.2126 - lr: 1.0000e-05 - 188ms/epoch - 4ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0500 - val_loss: 0.0598 - val_mse: 0.0598 - val_mae: 0.2125 - lr: 1.0000e-05 - 201ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0504 - val_loss: 0.0598 - val_mse: 0.0598 - val_mae: 0.2126 - lr: 1.0000e-05 - 218ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0500 - val_loss: 0.0599 - val_mse: 0.0599 - val_mae: 0.2128 - lr: 1.0000e-05 - 190ms/epoch - 4ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0493 - val_loss: 0.0597 - val_mse: 0.0597 - val_mae: 0.2124 - lr: 1.0000e-05 - 223ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0487 - val_loss: 0.0596 - val_mse: 0.0596 - val_mae: 0.2121 - lr: 1.0000e-05 - 198ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0496 - val_loss: 0.0594 - val_mse: 0.0594 - val_mae: 0.2118 - lr: 1.0000e-05 - 204ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0490 - val_loss: 0.0595 - val_mse: 0.0595 - val_mae: 0.2120 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0485 - val_loss: 0.0593 - val_mse: 0.0593 - val_mae: 0.2115 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0482 - val_loss: 0.0592 - val_mse: 0.0592 - val_mae: 0.2113 - lr: 1.0000e-05 - 187ms/epoch - 4ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0479 - val_loss: 0.0591 - val_mse: 0.0591 - val_mae: 0.2110 - lr: 1.0000e-05 - 224ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0487 - val_loss: 0.0589 - val_mse: 0.0589 - val_mae: 0.2107 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0473 - val_loss: 0.0589 - val_mse: 0.0589 - val_mae: 0.2106 - lr: 1.0000e-05 - 212ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0516 - val_loss: 0.0588 - val_mse: 0.0588 - val_mae: 0.2105 - lr: 1.0000e-05 - 195ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0502 - val_loss: 0.0585 - val_mse: 0.0585 - val_mae: 0.2097 - lr: 1.0000e-05 - 188ms/epoch - 4ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0490 - val_loss: 0.0584 - val_mse: 0.0584 - val_mae: 0.2096 - lr: 1.0000e-05 - 192ms/epoch - 4ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0506 - val_loss: 0.0582 - val_mse: 0.0582 - val_mae: 0.2091 - lr: 1.0000e-05 - 194ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0481 - val_loss: 0.0580 - val_mse: 0.0580 - val_mae: 0.2087 - lr: 1.0000e-05 - 208ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0496 - val_loss: 0.0578 - val_mse: 0.0578 - val_mae: 0.2083 - lr: 1.0000e-05 - 200ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0506 - val_loss: 0.0579 - val_mse: 0.0579 - val_mae: 0.2085 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0512 - val_loss: 0.0580 - val_mse: 0.0580 - val_mae: 0.2087 - lr: 1.0000e-05 - 215ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0486 - val_loss: 0.0576 - val_mse: 0.0576 - val_mae: 0.2079 - lr: 1.0000e-05 - 195ms/epoch - 4ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0489 - val_loss: 0.0577 - val_mse: 0.0577 - val_mae: 0.2080 - lr: 1.0000e-05 - 235ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0499 - val_loss: 0.0576 - val_mse: 0.0576 - val_mae: 0.2079 - lr: 1.0000e-05 - 193ms/epoch - 4ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0487 - val_loss: 0.0576 - val_mse: 0.0576 - val_mae: 0.2079 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0485 - val_loss: 0.0578 - val_mse: 0.0578 - val_mae: 0.2082 - lr: 1.0000e-05 - 184ms/epoch - 4ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0505 - val_loss: 0.0580 - val_mse: 0.0580 - val_mae: 0.2089 - lr: 1.0000e-05 - 211ms/epoch - 5ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0476 - val_loss: 0.0582 - val_mse: 0.0582 - val_mae: 0.2092 - lr: 1.0000e-05 - 205ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0485 - val_loss: 0.0582 - val_mse: 0.0582 - val_mae: 0.2091 - lr: 1.0000e-05 - 242ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0503 - val_loss: 0.0580 - val_mse: 0.0580 - val_mae: 0.2088 - lr: 1.0000e-05 - 179ms/epoch - 4ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0468 - val_loss: 0.0580 - val_mse: 0.0580 - val_mae: 0.2087 - lr: 1.0000e-05 - 223ms/epoch - 5ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0493 - val_loss: 0.0580 - val_mse: 0.0580 - val_mae: 0.2087 - lr: 1.0000e-05 - 266ms/epoch - 6ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0488 - val_loss: 0.0581 - val_mse: 0.0581 - val_mae: 0.2089 - lr: 1.0000e-05 - 199ms/epoch - 4ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.04341
45/45 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0488 - val_loss: 0.0581 - val_mse: 0.0581 - val_mae: 0.2091 - lr: 1.0000e-05 - 223ms/epoch - 5ms/step
Epoch 00063: early stopping

SMA
Prediction vs Close:		51.49% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 32.725767438505336 
RMSE:	 5.7206439706125165 
MAPE:	 4.798603095387009

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 143.9522591181831 
RMSE:	 11.998010631691534 
MAPE:	 10.07848404711658

WMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 24.586224407987817 
RMSE:	 4.958449798877449 
MAPE:	 3.970226889097132

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	51.49% Accuracy
MSE:	 207.2547601932076 
RMSE:	 14.3963453762824 
MAPE:	 12.894635987621164

KAMA
Prediction vs Close:		50.75% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 23.743754657069395 
RMSE:	 4.872756371610364 
MAPE:	 3.7850733762502107
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14

Working on MIDPOINT predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.35 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4212.289, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3747.746, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.26 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3523.401, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3387.759, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.24 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.84 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3389.758, Time=0.23 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.154 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1689.879
Date:                Sun, 12 Dec 2021   AIC                           3387.759
Time:                        15:05:27   BIC                           3406.522
Sample:                             0   HQIC                          3394.964
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1878      0.003   -345.315      0.000      -1.195      -1.181
ar.L2         -0.8876      0.007   -121.809      0.000      -0.902      -0.873
ar.L3         -0.3957      0.007    -60.127      0.000      -0.409      -0.383
sigma2         3.8904      0.020    193.404      0.000       3.851       3.930
===================================================================================
Ljung-Box (L1) (Q):                  13.21   Jarque-Bera (JB):           1659080.01
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.08   Skew:                             3.28
Prob(H) (two-sided):                  0.00   Kurtosis:                       225.31
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.09371, saving model to LSTM3.h5
58/58 - 3s - loss: 0.1380 - mse: 0.1380 - mae: 0.2774 - val_loss: 0.0937 - val_mse: 0.0937 - val_mae: 0.2769 - lr: 0.0010 - 3s/epoch - 48ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.09371 to 0.04685, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0497 - mse: 0.0497 - mae: 0.1767 - val_loss: 0.0468 - val_mse: 0.0468 - val_mae: 0.1731 - lr: 0.0010 - 303ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.04685 to 0.03945, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0222 - mse: 0.0222 - mae: 0.1174 - val_loss: 0.0395 - val_mse: 0.0395 - val_mae: 0.1598 - lr: 0.0010 - 277ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.03945
58/58 - 0s - loss: 0.0142 - mse: 0.0142 - mae: 0.0941 - val_loss: 0.0437 - val_mse: 0.0437 - val_mae: 0.1682 - lr: 0.0010 - 269ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.03945
58/58 - 0s - loss: 0.0143 - mse: 0.0143 - mae: 0.0960 - val_loss: 0.0416 - val_mse: 0.0416 - val_mae: 0.1632 - lr: 0.0010 - 241ms/epoch - 4ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.03945
58/58 - 0s - loss: 0.0115 - mse: 0.0115 - mae: 0.0853 - val_loss: 0.0458 - val_mse: 0.0458 - val_mae: 0.1734 - lr: 0.0010 - 275ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.03945
58/58 - 0s - loss: 0.0107 - mse: 0.0107 - mae: 0.0824 - val_loss: 0.0433 - val_mse: 0.0433 - val_mae: 0.1664 - lr: 0.0010 - 253ms/epoch - 4ms/step
Epoch 8/500

Epoch 00008: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00008: val_loss did not improve from 0.03945
58/58 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0704 - val_loss: 0.0470 - val_mse: 0.0470 - val_mae: 0.1766 - lr: 0.0010 - 252ms/epoch - 4ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.03945 to 0.03681, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0105 - mse: 0.0105 - mae: 0.0829 - val_loss: 0.0368 - val_mse: 0.0368 - val_mae: 0.1519 - lr: 1.0000e-04 - 287ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.03681 to 0.03586, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0717 - val_loss: 0.0359 - val_mse: 0.0359 - val_mae: 0.1489 - lr: 1.0000e-04 - 332ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.03586 to 0.03285, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0682 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1408 - lr: 1.0000e-04 - 299ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.03285
58/58 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0693 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1419 - lr: 1.0000e-04 - 243ms/epoch - 4ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.03285 to 0.03201, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0667 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1381 - lr: 1.0000e-04 - 273ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.03201 to 0.03175, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0645 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1373 - lr: 1.0000e-04 - 254ms/epoch - 4ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0618 - val_loss: 0.0325 - val_mse: 0.0325 - val_mae: 0.1391 - lr: 1.0000e-04 - 262ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0624 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1373 - lr: 1.0000e-04 - 245ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0587 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1394 - lr: 1.0000e-04 - 296ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0608 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1385 - lr: 1.0000e-04 - 292ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00019: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0595 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1399 - lr: 1.0000e-04 - 266ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0599 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1410 - lr: 1.0000e-05 - 277ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0561 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1409 - lr: 1.0000e-05 - 241ms/epoch - 4ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0576 - val_loss: 0.0330 - val_mse: 0.0330 - val_mae: 0.1407 - lr: 1.0000e-05 - 270ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0576 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1403 - lr: 1.0000e-05 - 250ms/epoch - 4ms/step
Epoch 24/500

Epoch 00024: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00024: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0573 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1400 - lr: 1.0000e-05 - 287ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0589 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1403 - lr: 1.0000e-05 - 243ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0558 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1410 - lr: 1.0000e-05 - 236ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0605 - val_loss: 0.0332 - val_mse: 0.0332 - val_mae: 0.1412 - lr: 1.0000e-05 - 247ms/epoch - 4ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0595 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1416 - lr: 1.0000e-05 - 280ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0584 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1416 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0591 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1424 - lr: 1.0000e-05 - 264ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0592 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1420 - lr: 1.0000e-05 - 270ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0568 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1423 - lr: 1.0000e-05 - 323ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0552 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1426 - lr: 1.0000e-05 - 293ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0592 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1437 - lr: 1.0000e-05 - 278ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0568 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1441 - lr: 1.0000e-05 - 293ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0576 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1444 - lr: 1.0000e-05 - 253ms/epoch - 4ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0558 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1444 - lr: 1.0000e-05 - 264ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0549 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1437 - lr: 1.0000e-05 - 254ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0574 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1438 - lr: 1.0000e-05 - 254ms/epoch - 4ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0543 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1424 - lr: 1.0000e-05 - 291ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0554 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1411 - lr: 1.0000e-05 - 254ms/epoch - 4ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0566 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1405 - lr: 1.0000e-05 - 292ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0572 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1392 - lr: 1.0000e-05 - 253ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0561 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1400 - lr: 1.0000e-05 - 265ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0545 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1403 - lr: 1.0000e-05 - 256ms/epoch - 4ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0588 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1404 - lr: 1.0000e-05 - 296ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0564 - val_loss: 0.0325 - val_mse: 0.0325 - val_mae: 0.1395 - lr: 1.0000e-05 - 269ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0553 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1390 - lr: 1.0000e-05 - 267ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0567 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1388 - lr: 1.0000e-05 - 266ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0551 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1392 - lr: 1.0000e-05 - 259ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0542 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1392 - lr: 1.0000e-05 - 242ms/epoch - 4ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0549 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1399 - lr: 1.0000e-05 - 266ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0537 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1402 - lr: 1.0000e-05 - 298ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0581 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1403 - lr: 1.0000e-05 - 270ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0524 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1405 - lr: 1.0000e-05 - 266ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0526 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1407 - lr: 1.0000e-05 - 257ms/epoch - 4ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0556 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1404 - lr: 1.0000e-05 - 290ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0536 - val_loss: 0.0325 - val_mse: 0.0325 - val_mae: 0.1397 - lr: 1.0000e-05 - 269ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0553 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1388 - lr: 1.0000e-05 - 241ms/epoch - 4ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0529 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1382 - lr: 1.0000e-05 - 283ms/epoch - 5ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.03175
58/58 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0579 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1384 - lr: 1.0000e-05 - 258ms/epoch - 4ms/step
Epoch 62/500

Epoch 00062: val_loss improved from 0.03175 to 0.03167, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0558 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1375 - lr: 1.0000e-05 - 441ms/epoch - 8ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0564 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1376 - lr: 1.0000e-05 - 293ms/epoch - 5ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0523 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1383 - lr: 1.0000e-05 - 269ms/epoch - 5ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0548 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1382 - lr: 1.0000e-05 - 303ms/epoch - 5ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0534 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1379 - lr: 1.0000e-05 - 276ms/epoch - 5ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0582 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1382 - lr: 1.0000e-05 - 286ms/epoch - 5ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0565 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1401 - lr: 1.0000e-05 - 236ms/epoch - 4ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0529 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1405 - lr: 1.0000e-05 - 274ms/epoch - 5ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0557 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1404 - lr: 1.0000e-05 - 329ms/epoch - 6ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0560 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1402 - lr: 1.0000e-05 - 270ms/epoch - 5ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0522 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1391 - lr: 1.0000e-05 - 267ms/epoch - 5ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0523 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1402 - lr: 1.0000e-05 - 272ms/epoch - 5ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0540 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1409 - lr: 1.0000e-05 - 291ms/epoch - 5ms/step
Epoch 75/500

Epoch 00075: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0526 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1411 - lr: 1.0000e-05 - 267ms/epoch - 5ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0541 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1416 - lr: 1.0000e-05 - 239ms/epoch - 4ms/step
Epoch 77/500

Epoch 00077: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0531 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1408 - lr: 1.0000e-05 - 289ms/epoch - 5ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0511 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1387 - lr: 1.0000e-05 - 288ms/epoch - 5ms/step
Epoch 79/500

Epoch 00079: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0516 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1384 - lr: 1.0000e-05 - 255ms/epoch - 4ms/step
Epoch 80/500

Epoch 00080: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0545 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1406 - lr: 1.0000e-05 - 251ms/epoch - 4ms/step
Epoch 81/500

Epoch 00081: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0536 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1390 - lr: 1.0000e-05 - 310ms/epoch - 5ms/step
Epoch 82/500

Epoch 00082: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0529 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1380 - lr: 1.0000e-05 - 246ms/epoch - 4ms/step
Epoch 83/500

Epoch 00083: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0511 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1380 - lr: 1.0000e-05 - 270ms/epoch - 5ms/step
Epoch 84/500

Epoch 00084: val_loss did not improve from 0.03167
58/58 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0547 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1393 - lr: 1.0000e-05 - 298ms/epoch - 5ms/step
Epoch 85/500

Epoch 00085: val_loss improved from 0.03167 to 0.03129, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0519 - val_loss: 0.0313 - val_mse: 0.0313 - val_mae: 0.1369 - lr: 1.0000e-05 - 428ms/epoch - 7ms/step
Epoch 86/500

Epoch 00086: val_loss did not improve from 0.03129
58/58 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0519 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1382 - lr: 1.0000e-05 - 269ms/epoch - 5ms/step
Epoch 87/500

Epoch 00087: val_loss did not improve from 0.03129
58/58 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0512 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1397 - lr: 1.0000e-05 - 300ms/epoch - 5ms/step
Epoch 88/500

Epoch 00088: val_loss did not improve from 0.03129
58/58 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0530 - val_loss: 0.0325 - val_mse: 0.0325 - val_mae: 0.1402 - lr: 1.0000e-05 - 292ms/epoch - 5ms/step
Epoch 89/500

Epoch 00089: val_loss did not improve from 0.03129
58/58 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0533 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1394 - lr: 1.0000e-05 - 296ms/epoch - 5ms/step
Epoch 90/500

Epoch 00090: val_loss did not improve from 0.03129
58/58 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0536 - val_loss: 0.0313 - val_mse: 0.0313 - val_mae: 0.1369 - lr: 1.0000e-05 - 247ms/epoch - 4ms/step
Epoch 91/500

Epoch 00091: val_loss improved from 0.03129 to 0.03083, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0522 - val_loss: 0.0308 - val_mse: 0.0308 - val_mae: 0.1357 - lr: 1.0000e-05 - 296ms/epoch - 5ms/step
Epoch 92/500

Epoch 00092: val_loss improved from 0.03083 to 0.03053, saving model to LSTM3.h5
58/58 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0515 - val_loss: 0.0305 - val_mse: 0.0305 - val_mae: 0.1349 - lr: 1.0000e-05 - 279ms/epoch - 5ms/step
Epoch 93/500

Epoch 00093: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0519 - val_loss: 0.0313 - val_mse: 0.0313 - val_mae: 0.1371 - lr: 1.0000e-05 - 258ms/epoch - 4ms/step
Epoch 94/500

Epoch 00094: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0518 - val_loss: 0.0314 - val_mse: 0.0314 - val_mae: 0.1373 - lr: 1.0000e-05 - 271ms/epoch - 5ms/step
Epoch 95/500

Epoch 00095: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0516 - val_loss: 0.0309 - val_mse: 0.0309 - val_mae: 0.1360 - lr: 1.0000e-05 - 251ms/epoch - 4ms/step
Epoch 96/500

Epoch 00096: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0534 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1361 - lr: 1.0000e-05 - 267ms/epoch - 5ms/step
Epoch 97/500

Epoch 00097: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0531 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1382 - lr: 1.0000e-05 - 260ms/epoch - 4ms/step
Epoch 98/500

Epoch 00098: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0512 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1361 - lr: 1.0000e-05 - 304ms/epoch - 5ms/step
Epoch 99/500

Epoch 00099: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0515 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1375 - lr: 1.0000e-05 - 246ms/epoch - 4ms/step
Epoch 100/500

Epoch 00100: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0516 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1377 - lr: 1.0000e-05 - 255ms/epoch - 4ms/step
Epoch 101/500

Epoch 00101: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0521 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1381 - lr: 1.0000e-05 - 299ms/epoch - 5ms/step
Epoch 102/500

Epoch 00102: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0528 - val_loss: 0.0313 - val_mse: 0.0313 - val_mae: 0.1369 - lr: 1.0000e-05 - 257ms/epoch - 4ms/step
Epoch 103/500

Epoch 00103: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0520 - val_loss: 0.0314 - val_mse: 0.0314 - val_mae: 0.1373 - lr: 1.0000e-05 - 247ms/epoch - 4ms/step
Epoch 104/500

Epoch 00104: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0495 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1386 - lr: 1.0000e-05 - 243ms/epoch - 4ms/step
Epoch 105/500

Epoch 00105: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0516 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1386 - lr: 1.0000e-05 - 254ms/epoch - 4ms/step
Epoch 106/500

Epoch 00106: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0523 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1377 - lr: 1.0000e-05 - 307ms/epoch - 5ms/step
Epoch 107/500

Epoch 00107: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0528 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1383 - lr: 1.0000e-05 - 247ms/epoch - 4ms/step
Epoch 108/500

Epoch 00108: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0499 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1377 - lr: 1.0000e-05 - 279ms/epoch - 5ms/step
Epoch 109/500

Epoch 00109: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0498 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1383 - lr: 1.0000e-05 - 301ms/epoch - 5ms/step
Epoch 110/500

Epoch 00110: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0471 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1383 - lr: 1.0000e-05 - 248ms/epoch - 4ms/step
Epoch 111/500

Epoch 00111: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0511 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1383 - lr: 1.0000e-05 - 247ms/epoch - 4ms/step
Epoch 112/500

Epoch 00112: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0497 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1382 - lr: 1.0000e-05 - 271ms/epoch - 5ms/step
Epoch 113/500

Epoch 00113: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0475 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1388 - lr: 1.0000e-05 - 341ms/epoch - 6ms/step
Epoch 114/500

Epoch 00114: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0509 - val_loss: 0.0314 - val_mse: 0.0314 - val_mae: 0.1371 - lr: 1.0000e-05 - 285ms/epoch - 5ms/step
Epoch 115/500

Epoch 00115: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0478 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1386 - lr: 1.0000e-05 - 260ms/epoch - 4ms/step
Epoch 116/500

Epoch 00116: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0486 - val_loss: 0.0325 - val_mse: 0.0325 - val_mae: 0.1403 - lr: 1.0000e-05 - 297ms/epoch - 5ms/step
Epoch 117/500

Epoch 00117: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0497 - val_loss: 0.0332 - val_mse: 0.0332 - val_mae: 0.1420 - lr: 1.0000e-05 - 288ms/epoch - 5ms/step
Epoch 118/500

Epoch 00118: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0528 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1425 - lr: 1.0000e-05 - 278ms/epoch - 5ms/step
Epoch 119/500

Epoch 00119: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0479 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1416 - lr: 1.0000e-05 - 276ms/epoch - 5ms/step
Epoch 120/500

Epoch 00120: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0493 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1404 - lr: 1.0000e-05 - 310ms/epoch - 5ms/step
Epoch 121/500

Epoch 00121: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0506 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1409 - lr: 1.0000e-05 - 252ms/epoch - 4ms/step
Epoch 122/500

Epoch 00122: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0514 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1418 - lr: 1.0000e-05 - 264ms/epoch - 5ms/step
Epoch 123/500

Epoch 00123: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0491 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1426 - lr: 1.0000e-05 - 298ms/epoch - 5ms/step
Epoch 124/500

Epoch 00124: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0496 - val_loss: 0.0332 - val_mse: 0.0332 - val_mae: 0.1419 - lr: 1.0000e-05 - 265ms/epoch - 5ms/step
Epoch 125/500

Epoch 00125: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0491 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1424 - lr: 1.0000e-05 - 252ms/epoch - 4ms/step
Epoch 126/500

Epoch 00126: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0501 - val_loss: 0.0332 - val_mse: 0.0332 - val_mae: 0.1420 - lr: 1.0000e-05 - 305ms/epoch - 5ms/step
Epoch 127/500

Epoch 00127: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0504 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1425 - lr: 1.0000e-05 - 251ms/epoch - 4ms/step
Epoch 128/500

Epoch 00128: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0495 - val_loss: 0.0325 - val_mse: 0.0325 - val_mae: 0.1401 - lr: 1.0000e-05 - 253ms/epoch - 4ms/step
Epoch 129/500

Epoch 00129: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0502 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1405 - lr: 1.0000e-05 - 268ms/epoch - 5ms/step
Epoch 130/500

Epoch 00130: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0506 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1396 - lr: 1.0000e-05 - 311ms/epoch - 5ms/step
Epoch 131/500

Epoch 00131: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0496 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1398 - lr: 1.0000e-05 - 290ms/epoch - 5ms/step
Epoch 132/500

Epoch 00132: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0503 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1409 - lr: 1.0000e-05 - 268ms/epoch - 5ms/step
Epoch 133/500

Epoch 00133: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0498 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1404 - lr: 1.0000e-05 - 272ms/epoch - 5ms/step
Epoch 134/500

Epoch 00134: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0473 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1418 - lr: 1.0000e-05 - 272ms/epoch - 5ms/step
Epoch 135/500

Epoch 00135: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0487 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1432 - lr: 1.0000e-05 - 252ms/epoch - 4ms/step
Epoch 136/500

Epoch 00136: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0496 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1446 - lr: 1.0000e-05 - 241ms/epoch - 4ms/step
Epoch 137/500

Epoch 00137: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0501 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1438 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 138/500

Epoch 00138: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0481 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1437 - lr: 1.0000e-05 - 268ms/epoch - 5ms/step
Epoch 139/500

Epoch 00139: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0506 - val_loss: 0.0340 - val_mse: 0.0340 - val_mae: 0.1441 - lr: 1.0000e-05 - 278ms/epoch - 5ms/step
Epoch 140/500

Epoch 00140: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0477 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1427 - lr: 1.0000e-05 - 259ms/epoch - 4ms/step
Epoch 141/500

Epoch 00141: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0483 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1424 - lr: 1.0000e-05 - 304ms/epoch - 5ms/step
Epoch 142/500

Epoch 00142: val_loss did not improve from 0.03053
58/58 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0485 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1422 - lr: 1.0000e-05 - 271ms/epoch - 5ms/step
Epoch 00142: early stopping

SMA
Prediction vs Close:		51.49% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 32.725767438505336 
RMSE:	 5.7206439706125165 
MAPE:	 4.798603095387009

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 143.9522591181831 
RMSE:	 11.998010631691534 
MAPE:	 10.07848404711658

WMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 24.586224407987817 
RMSE:	 4.958449798877449 
MAPE:	 3.970226889097132

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	51.49% Accuracy
MSE:	 207.2547601932076 
RMSE:	 14.3963453762824 
MAPE:	 12.894635987621164

KAMA
Prediction vs Close:		50.75% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 23.743754657069395 
RMSE:	 4.872756371610364 
MAPE:	 3.7850733762502107

MIDPOINT
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 35.62442093531873 
RMSE:	 5.968619684258559 
MAPE:	 5.0490603478808165
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19

Working on T3 predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.36 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4414.515, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3944.062, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.38 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3715.173, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3577.471, Time=0.10 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.42 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.58 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3579.471, Time=0.18 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.155 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1784.736
Date:                Sun, 12 Dec 2021   AIC                           3577.471
Time:                        15:07:20   BIC                           3596.235
Sample:                             0   HQIC                          3584.677
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.844      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.861      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.862      0.000      -0.410      -0.387
sigma2         4.9242      0.023    215.469      0.000       4.879       4.969
===================================================================================
Ljung-Box (L1) (Q):                  14.55   Jarque-Bera (JB):           2468024.38
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       274.15
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.11354, saving model to LSTM3.h5
43/43 - 2s - loss: 0.5101 - mse: 0.5101 - mae: 0.5223 - val_loss: 0.1135 - val_mse: 0.1135 - val_mae: 0.3053 - lr: 0.0010 - 2s/epoch - 53ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.11354 to 0.05364, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0361 - mse: 0.0361 - mae: 0.1535 - val_loss: 0.0536 - val_mse: 0.0536 - val_mae: 0.2042 - lr: 0.0010 - 214ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.05364 to 0.04216, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0328 - mse: 0.0328 - mae: 0.1459 - val_loss: 0.0422 - val_mse: 0.0422 - val_mae: 0.1788 - lr: 0.0010 - 236ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.04216 to 0.03063, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0282 - mse: 0.0282 - mae: 0.1364 - val_loss: 0.0306 - val_mse: 0.0306 - val_mae: 0.1492 - lr: 0.0010 - 244ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.03063 to 0.02455, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0227 - mse: 0.0227 - mae: 0.1199 - val_loss: 0.0246 - val_mse: 0.0246 - val_mae: 0.1304 - lr: 0.0010 - 224ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.02455
43/43 - 0s - loss: 0.0192 - mse: 0.0192 - mae: 0.1128 - val_loss: 0.0272 - val_mse: 0.0272 - val_mae: 0.1385 - lr: 0.0010 - 181ms/epoch - 4ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.02455
43/43 - 0s - loss: 0.0182 - mse: 0.0182 - mae: 0.1073 - val_loss: 0.0306 - val_mse: 0.0306 - val_mae: 0.1483 - lr: 0.0010 - 212ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.02455
43/43 - 0s - loss: 0.0170 - mse: 0.0170 - mae: 0.1051 - val_loss: 0.0278 - val_mse: 0.0278 - val_mae: 0.1389 - lr: 0.0010 - 211ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.02455 to 0.01847, saving model to LSTM3.h5
43/43 - 0s - loss: 0.0149 - mse: 0.0149 - mae: 0.0974 - val_loss: 0.0185 - val_mse: 0.0185 - val_mae: 0.1060 - lr: 0.0010 - 221ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0128 - mse: 0.0128 - mae: 0.0908 - val_loss: 0.0191 - val_mse: 0.0191 - val_mae: 0.1078 - lr: 0.0010 - 212ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0117 - mse: 0.0117 - mae: 0.0856 - val_loss: 0.0205 - val_mse: 0.0205 - val_mae: 0.1123 - lr: 0.0010 - 179ms/epoch - 4ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0105 - mse: 0.0105 - mae: 0.0826 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1476 - lr: 0.0010 - 235ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0093 - mse: 0.0093 - mae: 0.0758 - val_loss: 0.0247 - val_mse: 0.0247 - val_mae: 0.1261 - lr: 0.0010 - 186ms/epoch - 4ms/step
Epoch 14/500

Epoch 00014: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00014: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0088 - mse: 0.0088 - mae: 0.0740 - val_loss: 0.0260 - val_mse: 0.0260 - val_mae: 0.1306 - lr: 0.0010 - 183ms/epoch - 4ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0681 - val_loss: 0.0262 - val_mse: 0.0262 - val_mae: 0.1319 - lr: 1.0000e-04 - 197ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0692 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1309 - lr: 1.0000e-04 - 181ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0661 - val_loss: 0.0266 - val_mse: 0.0266 - val_mae: 0.1338 - lr: 1.0000e-04 - 235ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0650 - val_loss: 0.0279 - val_mse: 0.0279 - val_mae: 0.1384 - lr: 1.0000e-04 - 224ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00019: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0653 - val_loss: 0.0282 - val_mse: 0.0282 - val_mae: 0.1396 - lr: 1.0000e-04 - 202ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0643 - val_loss: 0.0283 - val_mse: 0.0283 - val_mae: 0.1399 - lr: 1.0000e-05 - 215ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0679 - val_loss: 0.0283 - val_mse: 0.0283 - val_mae: 0.1400 - lr: 1.0000e-05 - 184ms/epoch - 4ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0610 - val_loss: 0.0285 - val_mse: 0.0285 - val_mae: 0.1403 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0645 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1407 - lr: 1.0000e-05 - 228ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00024: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0647 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1408 - lr: 1.0000e-05 - 176ms/epoch - 4ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0632 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1408 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0639 - val_loss: 0.0284 - val_mse: 0.0284 - val_mae: 0.1403 - lr: 1.0000e-05 - 190ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0662 - val_loss: 0.0285 - val_mse: 0.0285 - val_mae: 0.1405 - lr: 1.0000e-05 - 219ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0663 - val_loss: 0.0284 - val_mse: 0.0284 - val_mae: 0.1402 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0652 - val_loss: 0.0285 - val_mse: 0.0285 - val_mae: 0.1406 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0631 - val_loss: 0.0287 - val_mse: 0.0287 - val_mae: 0.1412 - lr: 1.0000e-05 - 186ms/epoch - 4ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0633 - val_loss: 0.0288 - val_mse: 0.0288 - val_mae: 0.1414 - lr: 1.0000e-05 - 192ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0630 - val_loss: 0.0288 - val_mse: 0.0288 - val_mae: 0.1416 - lr: 1.0000e-05 - 186ms/epoch - 4ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0610 - val_loss: 0.0289 - val_mse: 0.0289 - val_mae: 0.1418 - lr: 1.0000e-05 - 218ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0646 - val_loss: 0.0289 - val_mse: 0.0289 - val_mae: 0.1418 - lr: 1.0000e-05 - 180ms/epoch - 4ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0627 - val_loss: 0.0287 - val_mse: 0.0287 - val_mae: 0.1413 - lr: 1.0000e-05 - 191ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0644 - val_loss: 0.0287 - val_mse: 0.0287 - val_mae: 0.1412 - lr: 1.0000e-05 - 206ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0654 - val_loss: 0.0284 - val_mse: 0.0284 - val_mae: 0.1405 - lr: 1.0000e-05 - 193ms/epoch - 4ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0636 - val_loss: 0.0283 - val_mse: 0.0283 - val_mae: 0.1401 - lr: 1.0000e-05 - 209ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0614 - val_loss: 0.0283 - val_mse: 0.0283 - val_mae: 0.1400 - lr: 1.0000e-05 - 210ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0642 - val_loss: 0.0284 - val_mse: 0.0284 - val_mae: 0.1404 - lr: 1.0000e-05 - 176ms/epoch - 4ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0655 - val_loss: 0.0284 - val_mse: 0.0284 - val_mae: 0.1403 - lr: 1.0000e-05 - 202ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0680 - val_loss: 0.0282 - val_mse: 0.0282 - val_mae: 0.1398 - lr: 1.0000e-05 - 204ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0646 - val_loss: 0.0282 - val_mse: 0.0282 - val_mae: 0.1400 - lr: 1.0000e-05 - 203ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0652 - val_loss: 0.0283 - val_mse: 0.0283 - val_mae: 0.1400 - lr: 1.0000e-05 - 216ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0652 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1397 - lr: 1.0000e-05 - 203ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0653 - val_loss: 0.0277 - val_mse: 0.0277 - val_mae: 0.1383 - lr: 1.0000e-05 - 184ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0609 - val_loss: 0.0277 - val_mse: 0.0277 - val_mae: 0.1383 - lr: 1.0000e-05 - 237ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0622 - val_loss: 0.0277 - val_mse: 0.0277 - val_mae: 0.1383 - lr: 1.0000e-05 - 254ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0618 - val_loss: 0.0277 - val_mse: 0.0277 - val_mae: 0.1383 - lr: 1.0000e-05 - 211ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0638 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1393 - lr: 1.0000e-05 - 187ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0654 - val_loss: 0.0282 - val_mse: 0.0282 - val_mae: 0.1398 - lr: 1.0000e-05 - 198ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0597 - val_loss: 0.0284 - val_mse: 0.0284 - val_mae: 0.1406 - lr: 1.0000e-05 - 181ms/epoch - 4ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0619 - val_loss: 0.0285 - val_mse: 0.0285 - val_mae: 0.1408 - lr: 1.0000e-05 - 224ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0623 - val_loss: 0.0287 - val_mse: 0.0287 - val_mae: 0.1415 - lr: 1.0000e-05 - 195ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0629 - val_loss: 0.0287 - val_mse: 0.0287 - val_mae: 0.1415 - lr: 1.0000e-05 - 193ms/epoch - 4ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0626 - val_loss: 0.0283 - val_mse: 0.0283 - val_mae: 0.1404 - lr: 1.0000e-05 - 212ms/epoch - 5ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0606 - val_loss: 0.0282 - val_mse: 0.0282 - val_mae: 0.1402 - lr: 1.0000e-05 - 233ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0633 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1395 - lr: 1.0000e-05 - 214ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.01847
43/43 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0613 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1399 - lr: 1.0000e-05 - 186ms/epoch - 4ms/step
Epoch 00059: early stopping

SMA
Prediction vs Close:		51.49% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 32.725767438505336 
RMSE:	 5.7206439706125165 
MAPE:	 4.798603095387009

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 143.9522591181831 
RMSE:	 11.998010631691534 
MAPE:	 10.07848404711658

WMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 24.586224407987817 
RMSE:	 4.958449798877449 
MAPE:	 3.970226889097132

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	51.49% Accuracy
MSE:	 207.2547601932076 
RMSE:	 14.3963453762824 
MAPE:	 12.894635987621164

KAMA
Prediction vs Close:		50.75% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 23.743754657069395 
RMSE:	 4.872756371610364 
MAPE:	 3.7850733762502107

MIDPOINT
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 35.62442093531873 
RMSE:	 5.968619684258559 
MAPE:	 5.0490603478808165

T3
Prediction vs Close:		56.34% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 103.73535640918065 
RMSE:	 10.185055542763655 
MAPE:	 8.016244139827235
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9

Working on TEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.47 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4352.703, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3889.412, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.26 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3689.930, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3574.245, Time=0.08 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.17 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.77 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3576.245, Time=0.17 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.053 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1783.123
Date:                Sun, 12 Dec 2021   AIC                           3574.245
Time:                        15:08:46   BIC                           3593.008
Sample:                             0   HQIC                          3581.451
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1480      0.004   -302.430      0.000      -1.155      -1.141
ar.L2         -0.8300      0.008    -99.682      0.000      -0.846      -0.814
ar.L3         -0.3687      0.007    -50.527      0.000      -0.383      -0.354
sigma2         4.9055      0.028    175.970      0.000       4.851       4.960
===================================================================================
Ljung-Box (L1) (Q):                  11.61   Jarque-Bera (JB):           1261976.58
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.16   Skew:                             2.52
Prob(H) (two-sided):                  0.00   Kurtosis:                       196.90
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.10461, saving model to LSTM3.h5
90/90 - 2s - loss: 0.0205 - mse: 0.0205 - mae: 0.1144 - val_loss: 0.1046 - val_mse: 0.1046 - val_mae: 0.2573 - lr: 0.0010 - 2s/epoch - 27ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.10461
90/90 - 0s - loss: 0.0231 - mse: 0.0231 - mae: 0.1277 - val_loss: 0.1193 - val_mse: 0.1193 - val_mae: 0.2715 - lr: 0.0010 - 362ms/epoch - 4ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.10461 to 0.07773, saving model to LSTM3.h5
90/90 - 0s - loss: 0.0539 - mse: 0.0539 - mae: 0.1890 - val_loss: 0.0777 - val_mse: 0.0777 - val_mae: 0.2154 - lr: 0.0010 - 378ms/epoch - 4ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.07773 to 0.04901, saving model to LSTM3.h5
90/90 - 0s - loss: 0.0338 - mse: 0.0338 - mae: 0.1354 - val_loss: 0.0490 - val_mse: 0.0490 - val_mae: 0.1713 - lr: 0.0010 - 382ms/epoch - 4ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0678 - val_loss: 0.0503 - val_mse: 0.0503 - val_mae: 0.1756 - lr: 0.0010 - 364ms/epoch - 4ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0622 - val_loss: 0.0663 - val_mse: 0.0663 - val_mae: 0.2078 - lr: 0.0010 - 376ms/epoch - 4ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0610 - val_loss: 0.0561 - val_mse: 0.0561 - val_mae: 0.1890 - lr: 0.0010 - 359ms/epoch - 4ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0627 - val_loss: 0.0839 - val_mse: 0.0839 - val_mae: 0.2436 - lr: 0.0010 - 380ms/epoch - 4ms/step
Epoch 9/500

Epoch 00009: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00009: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0646 - val_loss: 0.0571 - val_mse: 0.0571 - val_mae: 0.1908 - lr: 0.0010 - 374ms/epoch - 4ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0101 - mse: 0.0101 - mae: 0.0831 - val_loss: 0.0584 - val_mse: 0.0584 - val_mae: 0.1948 - lr: 1.0000e-04 - 372ms/epoch - 4ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0715 - val_loss: 0.0543 - val_mse: 0.0543 - val_mae: 0.1852 - lr: 1.0000e-04 - 354ms/epoch - 4ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0662 - val_loss: 0.0541 - val_mse: 0.0541 - val_mae: 0.1841 - lr: 1.0000e-04 - 381ms/epoch - 4ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0671 - val_loss: 0.0554 - val_mse: 0.0554 - val_mae: 0.1864 - lr: 1.0000e-04 - 369ms/epoch - 4ms/step
Epoch 14/500

Epoch 00014: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00014: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0632 - val_loss: 0.0577 - val_mse: 0.0577 - val_mae: 0.1909 - lr: 1.0000e-04 - 439ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0564 - val_loss: 0.0580 - val_mse: 0.0580 - val_mae: 0.1916 - lr: 1.0000e-05 - 393ms/epoch - 4ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0551 - val_loss: 0.0582 - val_mse: 0.0582 - val_mae: 0.1920 - lr: 1.0000e-05 - 379ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0600 - val_loss: 0.0585 - val_mse: 0.0585 - val_mae: 0.1926 - lr: 1.0000e-05 - 379ms/epoch - 4ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0583 - val_loss: 0.0589 - val_mse: 0.0589 - val_mae: 0.1934 - lr: 1.0000e-05 - 354ms/epoch - 4ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00019: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0595 - val_loss: 0.0593 - val_mse: 0.0593 - val_mae: 0.1942 - lr: 1.0000e-05 - 364ms/epoch - 4ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0582 - val_loss: 0.0594 - val_mse: 0.0594 - val_mae: 0.1944 - lr: 1.0000e-05 - 358ms/epoch - 4ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0566 - val_loss: 0.0594 - val_mse: 0.0594 - val_mae: 0.1945 - lr: 1.0000e-05 - 364ms/epoch - 4ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0549 - val_loss: 0.0600 - val_mse: 0.0600 - val_mae: 0.1956 - lr: 1.0000e-05 - 422ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0527 - val_loss: 0.0603 - val_mse: 0.0603 - val_mae: 0.1961 - lr: 1.0000e-05 - 358ms/epoch - 4ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0566 - val_loss: 0.0608 - val_mse: 0.0608 - val_mae: 0.1973 - lr: 1.0000e-05 - 364ms/epoch - 4ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0565 - val_loss: 0.0612 - val_mse: 0.0612 - val_mae: 0.1980 - lr: 1.0000e-05 - 354ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0554 - val_loss: 0.0614 - val_mse: 0.0614 - val_mae: 0.1985 - lr: 1.0000e-05 - 374ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0558 - val_loss: 0.0620 - val_mse: 0.0620 - val_mae: 0.1996 - lr: 1.0000e-05 - 364ms/epoch - 4ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0545 - val_loss: 0.0621 - val_mse: 0.0621 - val_mae: 0.2000 - lr: 1.0000e-05 - 372ms/epoch - 4ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0559 - val_loss: 0.0623 - val_mse: 0.0623 - val_mae: 0.2003 - lr: 1.0000e-05 - 355ms/epoch - 4ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0553 - val_loss: 0.0623 - val_mse: 0.0623 - val_mae: 0.2003 - lr: 1.0000e-05 - 394ms/epoch - 4ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0544 - val_loss: 0.0624 - val_mse: 0.0624 - val_mae: 0.2003 - lr: 1.0000e-05 - 354ms/epoch - 4ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0550 - val_loss: 0.0624 - val_mse: 0.0624 - val_mae: 0.2003 - lr: 1.0000e-05 - 359ms/epoch - 4ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0560 - val_loss: 0.0625 - val_mse: 0.0625 - val_mae: 0.2006 - lr: 1.0000e-05 - 382ms/epoch - 4ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0545 - val_loss: 0.0626 - val_mse: 0.0626 - val_mae: 0.2008 - lr: 1.0000e-05 - 353ms/epoch - 4ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0543 - val_loss: 0.0629 - val_mse: 0.0629 - val_mae: 0.2012 - lr: 1.0000e-05 - 362ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0535 - val_loss: 0.0632 - val_mse: 0.0632 - val_mae: 0.2019 - lr: 1.0000e-05 - 386ms/epoch - 4ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0519 - val_loss: 0.0634 - val_mse: 0.0634 - val_mae: 0.2023 - lr: 1.0000e-05 - 367ms/epoch - 4ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0529 - val_loss: 0.0638 - val_mse: 0.0638 - val_mae: 0.2029 - lr: 1.0000e-05 - 446ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0551 - val_loss: 0.0639 - val_mse: 0.0639 - val_mae: 0.2032 - lr: 1.0000e-05 - 440ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0537 - val_loss: 0.0646 - val_mse: 0.0646 - val_mae: 0.2046 - lr: 1.0000e-05 - 364ms/epoch - 4ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0532 - val_loss: 0.0647 - val_mse: 0.0647 - val_mae: 0.2047 - lr: 1.0000e-05 - 382ms/epoch - 4ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0527 - val_loss: 0.0653 - val_mse: 0.0653 - val_mae: 0.2060 - lr: 1.0000e-05 - 394ms/epoch - 4ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0533 - val_loss: 0.0657 - val_mse: 0.0657 - val_mae: 0.2068 - lr: 1.0000e-05 - 364ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0501 - val_loss: 0.0663 - val_mse: 0.0663 - val_mae: 0.2079 - lr: 1.0000e-05 - 360ms/epoch - 4ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0512 - val_loss: 0.0664 - val_mse: 0.0664 - val_mae: 0.2082 - lr: 1.0000e-05 - 354ms/epoch - 4ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0531 - val_loss: 0.0665 - val_mse: 0.0665 - val_mae: 0.2083 - lr: 1.0000e-05 - 365ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0524 - val_loss: 0.0670 - val_mse: 0.0670 - val_mae: 0.2093 - lr: 1.0000e-05 - 367ms/epoch - 4ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0041 - mse: 0.0041 - mae: 0.0509 - val_loss: 0.0678 - val_mse: 0.0678 - val_mae: 0.2108 - lr: 1.0000e-05 - 352ms/epoch - 4ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0493 - val_loss: 0.0678 - val_mse: 0.0678 - val_mae: 0.2109 - lr: 1.0000e-05 - 360ms/epoch - 4ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0517 - val_loss: 0.0683 - val_mse: 0.0683 - val_mae: 0.2118 - lr: 1.0000e-05 - 370ms/epoch - 4ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0516 - val_loss: 0.0686 - val_mse: 0.0686 - val_mae: 0.2123 - lr: 1.0000e-05 - 358ms/epoch - 4ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0509 - val_loss: 0.0690 - val_mse: 0.0690 - val_mae: 0.2132 - lr: 1.0000e-05 - 360ms/epoch - 4ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0513 - val_loss: 0.0694 - val_mse: 0.0694 - val_mae: 0.2139 - lr: 1.0000e-05 - 379ms/epoch - 4ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.04901
90/90 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0515 - val_loss: 0.0698 - val_mse: 0.0698 - val_mae: 0.2147 - lr: 1.0000e-05 - 363ms/epoch - 4ms/step
Epoch 00054: early stopping

SMA
Prediction vs Close:		51.49% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 32.725767438505336 
RMSE:	 5.7206439706125165 
MAPE:	 4.798603095387009

EMA
Prediction vs Close:		54.85% Accuracy
Prediction vs Prediction:	45.9% Accuracy
MSE:	 143.9522591181831 
RMSE:	 11.998010631691534 
MAPE:	 10.07848404711658

WMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 24.586224407987817 
RMSE:	 4.958449798877449 
MAPE:	 3.970226889097132

DEMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	51.49% Accuracy
MSE:	 207.2547601932076 
RMSE:	 14.3963453762824 
MAPE:	 12.894635987621164

KAMA
Prediction vs Close:		50.75% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 23.743754657069395 
RMSE:	 4.872756371610364 
MAPE:	 3.7850733762502107

MIDPOINT
Prediction vs Close:		50.0% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 35.62442093531873 
RMSE:	 5.968619684258559 
MAPE:	 5.0490603478808165

T3
Prediction vs Close:		56.34% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 103.73535640918065 
RMSE:	 10.185055542763655 
MAPE:	 8.016244139827235

TEMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	47.76% Accuracy
MSE:	 39.894741171517865 
RMSE:	 6.316228397668807 
MAPE:	 5.481705479796751
Runtime: mins: 12.72821348606667

Architecture Used¶

from google.colab import files
import cv2
uploaded = files.upload()

img = cv2.imread('Experiment3.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)

<matplotlib.image.AxesImage at 0x7fa5c4399110>

Model Plots¶

for i in range(len(list(simulation3.keys()))):
  SIM = list(simulation3.keys())[i]
  plot_train(simulation3,SIM)
  plot_test(simulation3,SIM)

----- Train RMSE for SMA ----- 9.155996008701845
----- Train_MSE_LSTM for SMA ----- 83.8322629113641
----- Train MAE LSTM for SMA ----- 8.009066904332526

----- Test RMSE for SMA----- 5.7206439706125165
----- Test_MSE_LSTM for SMA----- 32.725767438505336
----- Test_MAE_LSTM for SMA----- 4.798603095387009

----- Train RMSE for EMA ----- 10.577937809273275
----- Train_MSE_LSTM for EMA ----- 111.89276829685309
----- Train MAE LSTM for EMA ----- 9.432194934544697

----- Test RMSE for EMA----- 11.998010631691534
----- Test_MSE_LSTM for EMA----- 143.9522591181831
----- Test_MAE_LSTM for EMA----- 10.07848404711658

----- Train RMSE for WMA ----- 11.6464497844428
----- Train_MSE_LSTM for WMA ----- 135.63979258154774
----- Train MAE LSTM for WMA ----- 10.44059237611322

----- Test RMSE for WMA----- 4.958449798877449
----- Test_MSE_LSTM for WMA----- 24.586224407987817
----- Test_MAE_LSTM for WMA----- 3.970226889097132

----- Train RMSE for DEMA ----- 12.798003878729565
----- Train_MSE_LSTM for DEMA ----- 163.78890327997698
----- Train MAE LSTM for DEMA ----- 11.593951105370675

----- Test RMSE for DEMA----- 14.3963453762824
----- Test_MSE_LSTM for DEMA----- 207.2547601932076
----- Test_MAE_LSTM for DEMA----- 12.894635987621164

----- Train RMSE for KAMA ----- 10.917779337092348
----- Train_MSE_LSTM for KAMA ----- 119.19790565344064
----- Train MAE LSTM for KAMA ----- 9.91727143279415

----- Test RMSE for KAMA----- 4.872756371610364
----- Test_MSE_LSTM for KAMA----- 23.743754657069395
----- Test_MAE_LSTM for KAMA----- 3.7850733762502107

Univariate Arima Multistep MutiVariate LSTM Hybrid Model Experiment 4¶

From the above experiments it is evident that with Higher moving averages the loss plots show unreoresented data and underfitting, hence keeping only the MA's that have smaller periods like T3 OR TRIMA. Going forward EMA, WMA & DEMA will be ignored.

def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det = 20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # # Option 1
    # # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    # model.add(Dense(units=64,activation='relu'))
    # model.add(Dropout(0.5))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    # ## Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()


    # # option 2
    # model = Sequential()
    # model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    # model.add(Dense(64))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()




    # # Option 3
    # # define custom activation
    # # reference: https://github.com/Vaibhav-Sachdeva/Correlation-Coefficient-Prediction-using-ARIMA-LSTM-Hybrid-Model/blob/main/Code/LSTM-ARIMA.ipynb
    # class Double_Tanh(Activation):
    #     def __init__(self, activation, **kwargs):
    #         super(Double_Tanh, self).__init__(activation, **kwargs)
    #         self.__name__ = 'double_tanh'

    # def double_tanh(x):
    #     return (K.tanh(x) * 2)

    # get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
    #     # Model Generation
    # model = Sequential()
    # #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    # model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    # model.add(Dense(1))
    # model.add(Activation(double_tanh))
    # model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    model = Sequential()
    model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(input_dim, feature_size)))
    model.add(LSTM(units=int(lstm_len/2)))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(loss='mean_squared_error', optimizer='adam')
    # Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM4.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = (y_scaler.inverse_transform(predictiontr)-det).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte =( y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te

if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation4 = {}
    imgfile = 'Experiment4'
    for ma in optimized_period:
              print(ma)
              print(functions[ma])
              print ( int( optimized_period[ma]))
            # if ma == 'SMA':
              low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
              low_vol = low_vol.fillna(0)
              low_vol_data = df['close']
              high_vol = pd.DataFrame()
              df2 = df.copy()
              for i in df2.columns:
                if i in low_vol.columns:
                  high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
              high_vol_data = df['close']
              ## *****************************************************
              # Generate ARIMA and LSTM predictions
              print('\nWorking on ' + ma + ' predictions')
              try:
                print('parameters used : ', train_len, test_len)
                low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima(low_vol,low_vol_data, train_len, test_len)
              except:
                  print('ARIMA error, skipping to next MA type')
                  continue
              Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
              final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
              mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
              rmse_ftr = mse_ftr ** 0.5
              mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
              mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

              final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
              mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
              rmse = mse ** 0.5
              mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
              # Generate prediction accuracy
              actual = df['close'].tail(test_len).values
              result_1 = []
              result_2 = []
              for i in range(1, len(final_prediction)):
                  # Compare prediction to previous close price
                  if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                      result_1.append(1)
                  elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                      result_1.append(1)
                  else:
                      result_1.append(0)

                  # Compare prediction to previous prediction
                  if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                      result_2.append(1)
                  elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                      result_2.append(1)
                  else:
                      result_2.append(0)

              accuracy_1 = np.mean(result_1)
              accuracy_2 = np.mean(result_2)

              simulation4[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                            'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                            'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                            'rmse': rmse_ftr, 'mae' : mae_ftr},
                                'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                          'rmse': rmse, 'mae': mae },
                                'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

              # save simulation data here as checkpoint
              with open('simulation4_data.json', 'w') as fp:
                  json.dump(simulation4, fp)

              for ma in simulation4.keys():
                  print('\n' + ma)
                  print('Prediction vs Close:\t\t' + str(round(100*simulation4[ma]['accuracy']['prediction vs close'], 2))
                        + '% Accuracy')
                  print('Prediction vs Prediction:\t' + str(round(100*simulation4[ma]['accuracy']['prediction vs prediction'], 2))
                        + '% Accuracy')
                  print('MSE:\t', simulation4[ma]['final']['mse'],
                        '\nRMSE:\t', simulation4[ma]['final']['rmse'],
                        '\nMAPE:\t', simulation4[ma]['final']['mae'])#,
                        # '\nMAPE:\t', simulation[ma]['final']['mape'])
            # else:
            #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.54 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4157.020, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3687.148, Time=0.05 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.19 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3458.651, Time=0.08 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3322.133, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.76 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.82 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3324.133, Time=0.19 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.749 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1657.067
Date:                Sun, 12 Dec 2021   AIC                           3322.133
Time:                        15:18:11   BIC                           3340.897
Sample:                             0   HQIC                          3329.339
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1966      0.003   -387.226      0.000      -1.203      -1.191
ar.L2         -0.8952      0.006   -138.692      0.000      -0.908      -0.883
ar.L3         -0.3968      0.006    -68.284      0.000      -0.408      -0.385
sigma2         3.5858      0.017    214.535      0.000       3.553       3.619
===================================================================================
Ljung-Box (L1) (Q):                  14.47   Jarque-Bera (JB):           2428881.42
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       271.99
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.06157, saving model to LSTM4.h5
48/48 - 4s - loss: 1.3923 - val_loss: 0.0616 - lr: 0.0010 - 4s/epoch - 77ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.06157
48/48 - 0s - loss: 1.2621 - val_loss: 0.0663 - lr: 0.0010 - 263ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.06157
48/48 - 0s - loss: 1.1314 - val_loss: 0.0750 - lr: 0.0010 - 252ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.06157
48/48 - 0s - loss: 1.0246 - val_loss: 0.0868 - lr: 0.0010 - 278ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.9411 - val_loss: 0.0972 - lr: 0.0010 - 255ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8738 - val_loss: 0.1044 - lr: 0.0010 - 246ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8332 - val_loss: 0.1049 - lr: 1.0000e-04 - 243ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8268 - val_loss: 0.1054 - lr: 1.0000e-04 - 275ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8207 - val_loss: 0.1059 - lr: 1.0000e-04 - 243ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8147 - val_loss: 0.1064 - lr: 1.0000e-04 - 267ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8089 - val_loss: 0.1069 - lr: 1.0000e-04 - 261ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8053 - val_loss: 0.1070 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8047 - val_loss: 0.1070 - lr: 1.0000e-05 - 227ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8042 - val_loss: 0.1071 - lr: 1.0000e-05 - 239ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8036 - val_loss: 0.1071 - lr: 1.0000e-05 - 284ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8031 - val_loss: 0.1072 - lr: 1.0000e-05 - 277ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8025 - val_loss: 0.1073 - lr: 1.0000e-05 - 251ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8019 - val_loss: 0.1073 - lr: 1.0000e-05 - 244ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8014 - val_loss: 0.1074 - lr: 1.0000e-05 - 287ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8008 - val_loss: 0.1075 - lr: 1.0000e-05 - 252ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.8002 - val_loss: 0.1076 - lr: 1.0000e-05 - 240ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7997 - val_loss: 0.1076 - lr: 1.0000e-05 - 252ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7991 - val_loss: 0.1077 - lr: 1.0000e-05 - 318ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7985 - val_loss: 0.1078 - lr: 1.0000e-05 - 254ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7980 - val_loss: 0.1079 - lr: 1.0000e-05 - 278ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7974 - val_loss: 0.1079 - lr: 1.0000e-05 - 256ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7968 - val_loss: 0.1080 - lr: 1.0000e-05 - 280ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7963 - val_loss: 0.1081 - lr: 1.0000e-05 - 267ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7957 - val_loss: 0.1082 - lr: 1.0000e-05 - 234ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7951 - val_loss: 0.1083 - lr: 1.0000e-05 - 275ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7946 - val_loss: 0.1084 - lr: 1.0000e-05 - 252ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7940 - val_loss: 0.1084 - lr: 1.0000e-05 - 272ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7934 - val_loss: 0.1085 - lr: 1.0000e-05 - 239ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7929 - val_loss: 0.1086 - lr: 1.0000e-05 - 257ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7923 - val_loss: 0.1087 - lr: 1.0000e-05 - 254ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7917 - val_loss: 0.1088 - lr: 1.0000e-05 - 268ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7912 - val_loss: 0.1089 - lr: 1.0000e-05 - 268ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7906 - val_loss: 0.1090 - lr: 1.0000e-05 - 292ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7901 - val_loss: 0.1091 - lr: 1.0000e-05 - 245ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7895 - val_loss: 0.1091 - lr: 1.0000e-05 - 235ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7889 - val_loss: 0.1092 - lr: 1.0000e-05 - 247ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7884 - val_loss: 0.1093 - lr: 1.0000e-05 - 288ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7878 - val_loss: 0.1094 - lr: 1.0000e-05 - 257ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7873 - val_loss: 0.1095 - lr: 1.0000e-05 - 239ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7867 - val_loss: 0.1096 - lr: 1.0000e-05 - 279ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7862 - val_loss: 0.1097 - lr: 1.0000e-05 - 280ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7856 - val_loss: 0.1098 - lr: 1.0000e-05 - 250ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7850 - val_loss: 0.1099 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7845 - val_loss: 0.1100 - lr: 1.0000e-05 - 274ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7839 - val_loss: 0.1101 - lr: 1.0000e-05 - 260ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.06157
48/48 - 0s - loss: 0.7834 - val_loss: 0.1102 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 19.776724587061057 
RMSE:	 4.447102943159856 
MAPE:	 3.587879520041786
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.42 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4231.556, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3761.238, Time=0.05 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.28 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3532.227, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3394.496, Time=0.10 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.87 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.64 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3396.496, Time=0.22 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 2.687 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1693.248
Date:                Sun, 12 Dec 2021   AIC                           3394.496
Time:                        15:19:44   BIC                           3413.260
Sample:                             0   HQIC                          3401.702
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.569      0.000      -1.204      -1.192
ar.L2         -0.8976      0.006   -139.811      0.000      -0.910      -0.885
ar.L3         -0.3984      0.006    -68.662      0.000      -0.410      -0.387
sigma2         3.9230      0.018    215.372      0.000       3.887       3.959
===================================================================================
Ljung-Box (L1) (Q):                  14.54   Jarque-Bera (JB):           2462173.05
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.82
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.05562, saving model to LSTM4.h5
16/16 - 3s - loss: 1.4917 - val_loss: 0.0556 - lr: 0.0010 - 3s/epoch - 218ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.05562 to 0.05481, saving model to LSTM4.h5
16/16 - 0s - loss: 1.3932 - val_loss: 0.0548 - lr: 0.0010 - 146ms/epoch - 9ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.05481 to 0.05412, saving model to LSTM4.h5
16/16 - 0s - loss: 1.2699 - val_loss: 0.0541 - lr: 0.0010 - 129ms/epoch - 8ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.05412 to 0.05405, saving model to LSTM4.h5
16/16 - 0s - loss: 1.1744 - val_loss: 0.0540 - lr: 0.0010 - 131ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.1194 - val_loss: 0.0546 - lr: 0.0010 - 105ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0830 - val_loss: 0.0556 - lr: 0.0010 - 102ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0545 - val_loss: 0.0569 - lr: 0.0010 - 93ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00008: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0300 - val_loss: 0.0583 - lr: 0.0010 - 106ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0154 - val_loss: 0.0584 - lr: 1.0000e-04 - 92ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0133 - val_loss: 0.0586 - lr: 1.0000e-04 - 138ms/epoch - 9ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0112 - val_loss: 0.0587 - lr: 1.0000e-04 - 113ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0091 - val_loss: 0.0589 - lr: 1.0000e-04 - 109ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00013: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0071 - val_loss: 0.0591 - lr: 1.0000e-04 - 111ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0058 - val_loss: 0.0591 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0056 - val_loss: 0.0591 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0053 - val_loss: 0.0591 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0051 - val_loss: 0.0591 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00018: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0049 - val_loss: 0.0592 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0047 - val_loss: 0.0592 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0045 - val_loss: 0.0592 - lr: 1.0000e-05 - 119ms/epoch - 7ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0043 - val_loss: 0.0592 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0041 - val_loss: 0.0592 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0039 - val_loss: 0.0593 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0037 - val_loss: 0.0593 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0035 - val_loss: 0.0593 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0033 - val_loss: 0.0593 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0030 - val_loss: 0.0593 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0028 - val_loss: 0.0593 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0026 - val_loss: 0.0594 - lr: 1.0000e-05 - 125ms/epoch - 8ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0024 - val_loss: 0.0594 - lr: 1.0000e-05 - 117ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0022 - val_loss: 0.0594 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0020 - val_loss: 0.0594 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0018 - val_loss: 0.0594 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0016 - val_loss: 0.0595 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0013 - val_loss: 0.0595 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0011 - val_loss: 0.0595 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0009 - val_loss: 0.0595 - lr: 1.0000e-05 - 121ms/epoch - 8ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0007 - val_loss: 0.0596 - lr: 1.0000e-05 - 124ms/epoch - 8ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0005 - val_loss: 0.0596 - lr: 1.0000e-05 - 131ms/epoch - 8ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0003 - val_loss: 0.0596 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.05405
16/16 - 0s - loss: 1.0000 - val_loss: 0.0596 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9998 - val_loss: 0.0596 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9996 - val_loss: 0.0597 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9994 - val_loss: 0.0597 - lr: 1.0000e-05 - 124ms/epoch - 8ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9992 - val_loss: 0.0597 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9989 - val_loss: 0.0597 - lr: 1.0000e-05 - 144ms/epoch - 9ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9987 - val_loss: 0.0597 - lr: 1.0000e-05 - 117ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9985 - val_loss: 0.0598 - lr: 1.0000e-05 - 120ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9983 - val_loss: 0.0598 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9981 - val_loss: 0.0598 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9979 - val_loss: 0.0598 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9976 - val_loss: 0.0599 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9974 - val_loss: 0.0599 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.05405
16/16 - 0s - loss: 0.9972 - val_loss: 0.0599 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 00054: early stopping

SMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 19.776724587061057 
RMSE:	 4.447102943159856 
MAPE:	 3.587879520041786

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	48.88% Accuracy
MSE:	 31.621751516368622 
RMSE:	 5.623322106759368 
MAPE:	 4.355106062590965
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.43 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4264.089, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3793.930, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.24 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3564.923, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3427.258, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.30 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.46 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3429.258, Time=0.69 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.352 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1709.629
Date:                Sun, 12 Dec 2021   AIC                           3427.258
Time:                        15:21:04   BIC                           3446.021
Sample:                             0   HQIC                          3434.464
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1981      0.003   -389.386      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.699      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.737      0.000      -0.410      -0.387
sigma2         4.0860      0.019    215.311      0.000       4.049       4.123
===================================================================================
Ljung-Box (L1) (Q):                  14.57   Jarque-Bera (JB):           2460901.70
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.75
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04594, saving model to LSTM4.h5
17/17 - 4s - loss: 1.3787 - val_loss: 0.0459 - lr: 0.0010 - 4s/epoch - 208ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.3437 - val_loss: 0.0469 - lr: 0.0010 - 93ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.3089 - val_loss: 0.0478 - lr: 0.0010 - 104ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.2753 - val_loss: 0.0487 - lr: 0.0010 - 107ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.2443 - val_loss: 0.0495 - lr: 0.0010 - 104ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.2162 - val_loss: 0.0506 - lr: 0.0010 - 104ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1992 - val_loss: 0.0507 - lr: 1.0000e-04 - 112ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1968 - val_loss: 0.0508 - lr: 1.0000e-04 - 105ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1943 - val_loss: 0.0509 - lr: 1.0000e-04 - 107ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1919 - val_loss: 0.0511 - lr: 1.0000e-04 - 105ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1895 - val_loss: 0.0512 - lr: 1.0000e-04 - 104ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1880 - val_loss: 0.0512 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1878 - val_loss: 0.0512 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1875 - val_loss: 0.0512 - lr: 1.0000e-05 - 119ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1873 - val_loss: 0.0513 - lr: 1.0000e-05 - 135ms/epoch - 8ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1870 - val_loss: 0.0513 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1868 - val_loss: 0.0513 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1866 - val_loss: 0.0513 - lr: 1.0000e-05 - 125ms/epoch - 7ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1863 - val_loss: 0.0513 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1861 - val_loss: 0.0513 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1859 - val_loss: 0.0514 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1856 - val_loss: 0.0514 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1854 - val_loss: 0.0514 - lr: 1.0000e-05 - 120ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1851 - val_loss: 0.0514 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1849 - val_loss: 0.0514 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1847 - val_loss: 0.0514 - lr: 1.0000e-05 - 123ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1844 - val_loss: 0.0514 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1842 - val_loss: 0.0515 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1839 - val_loss: 0.0515 - lr: 1.0000e-05 - 106ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1837 - val_loss: 0.0515 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1835 - val_loss: 0.0515 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1832 - val_loss: 0.0515 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1830 - val_loss: 0.0516 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1827 - val_loss: 0.0516 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1825 - val_loss: 0.0516 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1823 - val_loss: 0.0516 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1820 - val_loss: 0.0516 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1818 - val_loss: 0.0516 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1815 - val_loss: 0.0517 - lr: 1.0000e-05 - 116ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1813 - val_loss: 0.0517 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1811 - val_loss: 0.0517 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1808 - val_loss: 0.0517 - lr: 1.0000e-05 - 126ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1806 - val_loss: 0.0517 - lr: 1.0000e-05 - 121ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1803 - val_loss: 0.0518 - lr: 1.0000e-05 - 110ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1801 - val_loss: 0.0518 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1799 - val_loss: 0.0518 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1796 - val_loss: 0.0518 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1794 - val_loss: 0.0518 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1792 - val_loss: 0.0519 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1789 - val_loss: 0.0519 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04594
17/17 - 0s - loss: 1.1787 - val_loss: 0.0519 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 19.776724587061057 
RMSE:	 4.447102943159856 
MAPE:	 3.587879520041786

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	48.88% Accuracy
MSE:	 31.621751516368622 
RMSE:	 5.623322106759368 
MAPE:	 4.355106062590965

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 52.4753296205182 
RMSE:	 7.2439857551294375 
MAPE:	 5.852253139584933
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.44 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4436.126, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3965.317, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.37 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3736.589, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3598.951, Time=0.08 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=0.95 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.94 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3600.951, Time=0.18 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.101 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1795.475
Date:                Sun, 12 Dec 2021   AIC                           3598.951
Time:                        15:22:26   BIC                           3617.714
Sample:                             0   HQIC                          3606.157
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1983      0.003   -389.581      0.000      -1.204      -1.192
ar.L2         -0.8973      0.006   -139.732      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.649      0.000      -0.410      -0.387
sigma2         5.0573      0.023    215.292      0.000       5.011       5.103
===================================================================================
Ljung-Box (L1) (Q):                  14.41   Jarque-Bera (JB):           2460553.80
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.89
Prob(H) (two-sided):                  0.00   Kurtosis:                       273.74
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04142, saving model to LSTM4.h5
10/10 - 4s - loss: 1.3181 - val_loss: 0.0414 - lr: 0.0010 - 4s/epoch - 374ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.04142 to 0.04094, saving model to LSTM4.h5
10/10 - 0s - loss: 1.2515 - val_loss: 0.0409 - lr: 0.0010 - 90ms/epoch - 9ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.04094 to 0.04051, saving model to LSTM4.h5
10/10 - 0s - loss: 1.1982 - val_loss: 0.0405 - lr: 0.0010 - 84ms/epoch - 8ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.04051 to 0.04014, saving model to LSTM4.h5
10/10 - 0s - loss: 1.1531 - val_loss: 0.0401 - lr: 0.0010 - 81ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.04014 to 0.03983, saving model to LSTM4.h5
10/10 - 0s - loss: 1.1133 - val_loss: 0.0398 - lr: 0.0010 - 98ms/epoch - 10ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.03983 to 0.03959, saving model to LSTM4.h5
10/10 - 0s - loss: 1.0771 - val_loss: 0.0396 - lr: 0.0010 - 85ms/epoch - 8ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.03959 to 0.03942, saving model to LSTM4.h5
10/10 - 0s - loss: 1.0439 - val_loss: 0.0394 - lr: 0.0010 - 80ms/epoch - 8ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.03942 to 0.03934, saving model to LSTM4.h5
10/10 - 0s - loss: 1.0138 - val_loss: 0.0393 - lr: 0.0010 - 84ms/epoch - 8ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9873 - val_loss: 0.0394 - lr: 0.0010 - 90ms/epoch - 9ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9643 - val_loss: 0.0395 - lr: 0.0010 - 106ms/epoch - 11ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9445 - val_loss: 0.0397 - lr: 0.0010 - 84ms/epoch - 8ms/step
Epoch 12/500

Epoch 00012: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00012: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9272 - val_loss: 0.0400 - lr: 0.0010 - 84ms/epoch - 8ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9162 - val_loss: 0.0400 - lr: 1.0000e-04 - 79ms/epoch - 8ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9148 - val_loss: 0.0401 - lr: 1.0000e-04 - 77ms/epoch - 8ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9134 - val_loss: 0.0401 - lr: 1.0000e-04 - 88ms/epoch - 9ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9120 - val_loss: 0.0401 - lr: 1.0000e-04 - 79ms/epoch - 8ms/step
Epoch 17/500

Epoch 00017: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00017: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9106 - val_loss: 0.0402 - lr: 1.0000e-04 - 71ms/epoch - 7ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9096 - val_loss: 0.0402 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9095 - val_loss: 0.0402 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9093 - val_loss: 0.0402 - lr: 1.0000e-05 - 77ms/epoch - 8ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9092 - val_loss: 0.0402 - lr: 1.0000e-05 - 86ms/epoch - 9ms/step
Epoch 22/500

Epoch 00022: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00022: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9091 - val_loss: 0.0402 - lr: 1.0000e-05 - 102ms/epoch - 10ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9089 - val_loss: 0.0402 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9088 - val_loss: 0.0402 - lr: 1.0000e-05 - 88ms/epoch - 9ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9087 - val_loss: 0.0402 - lr: 1.0000e-05 - 107ms/epoch - 11ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9085 - val_loss: 0.0402 - lr: 1.0000e-05 - 81ms/epoch - 8ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9084 - val_loss: 0.0402 - lr: 1.0000e-05 - 81ms/epoch - 8ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9082 - val_loss: 0.0402 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9081 - val_loss: 0.0402 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9079 - val_loss: 0.0402 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9078 - val_loss: 0.0402 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9077 - val_loss: 0.0402 - lr: 1.0000e-05 - 80ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9075 - val_loss: 0.0402 - lr: 1.0000e-05 - 82ms/epoch - 8ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9074 - val_loss: 0.0403 - lr: 1.0000e-05 - 95ms/epoch - 10ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9072 - val_loss: 0.0403 - lr: 1.0000e-05 - 97ms/epoch - 10ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9071 - val_loss: 0.0403 - lr: 1.0000e-05 - 75ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9069 - val_loss: 0.0403 - lr: 1.0000e-05 - 79ms/epoch - 8ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9068 - val_loss: 0.0403 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9066 - val_loss: 0.0403 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9065 - val_loss: 0.0403 - lr: 1.0000e-05 - 89ms/epoch - 9ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9064 - val_loss: 0.0403 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9062 - val_loss: 0.0403 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9061 - val_loss: 0.0403 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9059 - val_loss: 0.0403 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9058 - val_loss: 0.0403 - lr: 1.0000e-05 - 92ms/epoch - 9ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9056 - val_loss: 0.0403 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9055 - val_loss: 0.0403 - lr: 1.0000e-05 - 90ms/epoch - 9ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9053 - val_loss: 0.0403 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9052 - val_loss: 0.0403 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9050 - val_loss: 0.0403 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9049 - val_loss: 0.0403 - lr: 1.0000e-05 - 80ms/epoch - 8ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9047 - val_loss: 0.0403 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9046 - val_loss: 0.0404 - lr: 1.0000e-05 - 86ms/epoch - 9ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9044 - val_loss: 0.0404 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9043 - val_loss: 0.0404 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9041 - val_loss: 0.0404 - lr: 1.0000e-05 - 80ms/epoch - 8ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9040 - val_loss: 0.0404 - lr: 1.0000e-05 - 93ms/epoch - 9ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.03934
10/10 - 0s - loss: 0.9038 - val_loss: 0.0404 - lr: 1.0000e-05 - 75ms/epoch - 7ms/step
Epoch 00058: early stopping

SMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 19.776724587061057 
RMSE:	 4.447102943159856 
MAPE:	 3.587879520041786

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	48.88% Accuracy
MSE:	 31.621751516368622 
RMSE:	 5.623322106759368 
MAPE:	 4.355106062590965

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 52.4753296205182 
RMSE:	 7.2439857551294375 
MAPE:	 5.852253139584933

DEMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 146.44755629127866 
RMSE:	 12.10155181335347 
MAPE:	 10.943210296434415
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.37 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4190.464, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3724.371, Time=0.05 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.29 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3494.154, Time=0.07 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3357.435, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.17 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.74 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3359.435, Time=0.21 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.041 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1674.717
Date:                Sun, 12 Dec 2021   AIC                           3357.435
Time:                        15:23:44   BIC                           3376.198
Sample:                             0   HQIC                          3364.641
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1955      0.003   -381.246      0.000      -1.202      -1.189
ar.L2         -0.8964      0.007   -135.835      0.000      -0.909      -0.883
ar.L3         -0.3971      0.006    -67.229      0.000      -0.409      -0.385
sigma2         3.7466      0.018    211.623      0.000       3.712       3.781
===================================================================================
Ljung-Box (L1) (Q):                  14.20   Jarque-Bera (JB):           2338363.32
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             3.76
Prob(H) (two-sided):                  0.00   Kurtosis:                       266.93
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.05310, saving model to LSTM4.h5
45/45 - 4s - loss: 1.2968 - val_loss: 0.0531 - lr: 0.0010 - 4s/epoch - 90ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.05310
45/45 - 0s - loss: 1.0725 - val_loss: 0.0568 - lr: 0.0010 - 315ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.9746 - val_loss: 0.0608 - lr: 0.0010 - 274ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.9066 - val_loss: 0.0645 - lr: 0.0010 - 248ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.8542 - val_loss: 0.0681 - lr: 0.0010 - 269ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.8135 - val_loss: 0.0717 - lr: 0.0010 - 257ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7928 - val_loss: 0.0721 - lr: 1.0000e-04 - 266ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7898 - val_loss: 0.0724 - lr: 1.0000e-04 - 289ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7868 - val_loss: 0.0728 - lr: 1.0000e-04 - 285ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7838 - val_loss: 0.0732 - lr: 1.0000e-04 - 306ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7808 - val_loss: 0.0736 - lr: 1.0000e-04 - 256ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7790 - val_loss: 0.0737 - lr: 1.0000e-05 - 272ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7787 - val_loss: 0.0737 - lr: 1.0000e-05 - 262ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7784 - val_loss: 0.0738 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7781 - val_loss: 0.0738 - lr: 1.0000e-05 - 240ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7778 - val_loss: 0.0739 - lr: 1.0000e-05 - 253ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7774 - val_loss: 0.0739 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7771 - val_loss: 0.0740 - lr: 1.0000e-05 - 258ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7768 - val_loss: 0.0740 - lr: 1.0000e-05 - 268ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7765 - val_loss: 0.0740 - lr: 1.0000e-05 - 255ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7761 - val_loss: 0.0741 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7758 - val_loss: 0.0742 - lr: 1.0000e-05 - 249ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7755 - val_loss: 0.0742 - lr: 1.0000e-05 - 252ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7751 - val_loss: 0.0743 - lr: 1.0000e-05 - 286ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7748 - val_loss: 0.0743 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7744 - val_loss: 0.0744 - lr: 1.0000e-05 - 231ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7741 - val_loss: 0.0744 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7737 - val_loss: 0.0745 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7734 - val_loss: 0.0745 - lr: 1.0000e-05 - 260ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7730 - val_loss: 0.0746 - lr: 1.0000e-05 - 269ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7727 - val_loss: 0.0746 - lr: 1.0000e-05 - 280ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7723 - val_loss: 0.0747 - lr: 1.0000e-05 - 266ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7720 - val_loss: 0.0748 - lr: 1.0000e-05 - 230ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7716 - val_loss: 0.0748 - lr: 1.0000e-05 - 258ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7713 - val_loss: 0.0749 - lr: 1.0000e-05 - 251ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7709 - val_loss: 0.0749 - lr: 1.0000e-05 - 235ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7706 - val_loss: 0.0750 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7702 - val_loss: 0.0751 - lr: 1.0000e-05 - 251ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7698 - val_loss: 0.0751 - lr: 1.0000e-05 - 245ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7695 - val_loss: 0.0752 - lr: 1.0000e-05 - 227ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7691 - val_loss: 0.0753 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7688 - val_loss: 0.0753 - lr: 1.0000e-05 - 230ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7684 - val_loss: 0.0754 - lr: 1.0000e-05 - 261ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7681 - val_loss: 0.0755 - lr: 1.0000e-05 - 237ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7677 - val_loss: 0.0755 - lr: 1.0000e-05 - 249ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7673 - val_loss: 0.0756 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7670 - val_loss: 0.0757 - lr: 1.0000e-05 - 239ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7666 - val_loss: 0.0757 - lr: 1.0000e-05 - 253ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7663 - val_loss: 0.0758 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7659 - val_loss: 0.0759 - lr: 1.0000e-05 - 253ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.05310
45/45 - 0s - loss: 0.7655 - val_loss: 0.0759 - lr: 1.0000e-05 - 294ms/epoch - 7ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 19.776724587061057 
RMSE:	 4.447102943159856 
MAPE:	 3.587879520041786

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	48.88% Accuracy
MSE:	 31.621751516368622 
RMSE:	 5.623322106759368 
MAPE:	 4.355106062590965

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 52.4753296205182 
RMSE:	 7.2439857551294375 
MAPE:	 5.852253139584933

DEMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 146.44755629127866 
RMSE:	 12.10155181335347 
MAPE:	 10.943210296434415

KAMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 19.64215945229788 
RMSE:	 4.4319475913302355 
MAPE:	 3.5686191181651687
MIDPOINT
MIDPOINT([input_arrays], [timeperiod=14])

MidPoint over period (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 14
Outputs:
    real
14

Working on MIDPOINT predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.37 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4212.289, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3747.746, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.23 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3523.401, Time=0.08 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3387.759, Time=0.12 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.30 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.88 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3389.758, Time=0.24 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.287 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1689.879
Date:                Sun, 12 Dec 2021   AIC                           3387.759
Time:                        15:25:11   BIC                           3406.522
Sample:                             0   HQIC                          3394.964
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1878      0.003   -345.315      0.000      -1.195      -1.181
ar.L2         -0.8876      0.007   -121.809      0.000      -0.902      -0.873
ar.L3         -0.3957      0.007    -60.127      0.000      -0.409      -0.383
sigma2         3.8904      0.020    193.404      0.000       3.851       3.930
===================================================================================
Ljung-Box (L1) (Q):                  13.21   Jarque-Bera (JB):           1659080.01
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.08   Skew:                             3.28
Prob(H) (two-sided):                  0.00   Kurtosis:                       225.31
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04095, saving model to LSTM4.h5
58/58 - 4s - loss: 1.2983 - val_loss: 0.0410 - lr: 0.0010 - 4s/epoch - 63ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04095
58/58 - 0s - loss: 1.1355 - val_loss: 0.0436 - lr: 0.0010 - 310ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04095
58/58 - 0s - loss: 1.0175 - val_loss: 0.0468 - lr: 0.0010 - 329ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.9394 - val_loss: 0.0508 - lr: 0.0010 - 284ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8828 - val_loss: 0.0556 - lr: 0.0010 - 318ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8400 - val_loss: 0.0610 - lr: 0.0010 - 311ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8176 - val_loss: 0.0616 - lr: 1.0000e-04 - 310ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8144 - val_loss: 0.0622 - lr: 1.0000e-04 - 322ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8111 - val_loss: 0.0628 - lr: 1.0000e-04 - 332ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8078 - val_loss: 0.0634 - lr: 1.0000e-04 - 325ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8045 - val_loss: 0.0640 - lr: 1.0000e-04 - 309ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8025 - val_loss: 0.0641 - lr: 1.0000e-05 - 323ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8022 - val_loss: 0.0641 - lr: 1.0000e-05 - 296ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8018 - val_loss: 0.0642 - lr: 1.0000e-05 - 312ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8015 - val_loss: 0.0643 - lr: 1.0000e-05 - 291ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8011 - val_loss: 0.0644 - lr: 1.0000e-05 - 303ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8008 - val_loss: 0.0644 - lr: 1.0000e-05 - 314ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8004 - val_loss: 0.0645 - lr: 1.0000e-05 - 288ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.8001 - val_loss: 0.0646 - lr: 1.0000e-05 - 289ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7997 - val_loss: 0.0647 - lr: 1.0000e-05 - 282ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7994 - val_loss: 0.0648 - lr: 1.0000e-05 - 308ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7990 - val_loss: 0.0648 - lr: 1.0000e-05 - 318ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7987 - val_loss: 0.0649 - lr: 1.0000e-05 - 291ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7983 - val_loss: 0.0650 - lr: 1.0000e-05 - 310ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7979 - val_loss: 0.0651 - lr: 1.0000e-05 - 290ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7976 - val_loss: 0.0652 - lr: 1.0000e-05 - 342ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7972 - val_loss: 0.0653 - lr: 1.0000e-05 - 316ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7968 - val_loss: 0.0654 - lr: 1.0000e-05 - 292ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7965 - val_loss: 0.0655 - lr: 1.0000e-05 - 308ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7961 - val_loss: 0.0656 - lr: 1.0000e-05 - 300ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7957 - val_loss: 0.0657 - lr: 1.0000e-05 - 310ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7953 - val_loss: 0.0658 - lr: 1.0000e-05 - 294ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7950 - val_loss: 0.0659 - lr: 1.0000e-05 - 290ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7946 - val_loss: 0.0660 - lr: 1.0000e-05 - 333ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7942 - val_loss: 0.0661 - lr: 1.0000e-05 - 315ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7938 - val_loss: 0.0662 - lr: 1.0000e-05 - 291ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7935 - val_loss: 0.0663 - lr: 1.0000e-05 - 323ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7931 - val_loss: 0.0664 - lr: 1.0000e-05 - 323ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7927 - val_loss: 0.0665 - lr: 1.0000e-05 - 332ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7923 - val_loss: 0.0666 - lr: 1.0000e-05 - 344ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7920 - val_loss: 0.0667 - lr: 1.0000e-05 - 293ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7916 - val_loss: 0.0668 - lr: 1.0000e-05 - 322ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7912 - val_loss: 0.0669 - lr: 1.0000e-05 - 312ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7908 - val_loss: 0.0670 - lr: 1.0000e-05 - 287ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7905 - val_loss: 0.0671 - lr: 1.0000e-05 - 317ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7901 - val_loss: 0.0672 - lr: 1.0000e-05 - 326ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7897 - val_loss: 0.0674 - lr: 1.0000e-05 - 306ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7893 - val_loss: 0.0675 - lr: 1.0000e-05 - 323ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7890 - val_loss: 0.0676 - lr: 1.0000e-05 - 312ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7886 - val_loss: 0.0677 - lr: 1.0000e-05 - 329ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04095
58/58 - 0s - loss: 0.7882 - val_loss: 0.0678 - lr: 1.0000e-05 - 313ms/epoch - 5ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 19.776724587061057 
RMSE:	 4.447102943159856 
MAPE:	 3.587879520041786

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	48.88% Accuracy
MSE:	 31.621751516368622 
RMSE:	 5.623322106759368 
MAPE:	 4.355106062590965

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 52.4753296205182 
RMSE:	 7.2439857551294375 
MAPE:	 5.852253139584933

DEMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 146.44755629127866 
RMSE:	 12.10155181335347 
MAPE:	 10.943210296434415

KAMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 19.64215945229788 
RMSE:	 4.4319475913302355 
MAPE:	 3.5686191181651687

MIDPOINT
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	45.52% Accuracy
MSE:	 19.83404242536117 
RMSE:	 4.453542682557468 
MAPE:	 3.5743844299716057
T3
T3([input_arrays], [timeperiod=5], [vfactor=0.7])

Triple Exponential Moving Average (T3) (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 5
    vfactor: 0.7
Outputs:
    real
19

Working on T3 predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.35 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4414.515, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3944.062, Time=0.04 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.36 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3715.173, Time=0.06 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3577.471, Time=0.09 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.39 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.60 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3579.471, Time=0.19 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.115 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1784.736
Date:                Sun, 12 Dec 2021   AIC                           3577.471
Time:                        15:26:44   BIC                           3596.235
Sample:                             0   HQIC                          3584.677
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1982      0.003   -389.844      0.000      -1.204      -1.192
ar.L2         -0.8974      0.006   -139.861      0.000      -0.910      -0.885
ar.L3         -0.3983      0.006    -68.862      0.000      -0.410      -0.387
sigma2         4.9242      0.023    215.469      0.000       4.879       4.969
===================================================================================
Ljung-Box (L1) (Q):                  14.55   Jarque-Bera (JB):           2468024.38
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             3.90
Prob(H) (two-sided):                  0.00   Kurtosis:                       274.15
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04951, saving model to LSTM4.h5
43/43 - 4s - loss: 1.4093 - val_loss: 0.0495 - lr: 0.0010 - 4s/epoch - 83ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.3586 - val_loss: 0.0516 - lr: 0.0010 - 248ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.3003 - val_loss: 0.0540 - lr: 0.0010 - 227ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.2446 - val_loss: 0.0567 - lr: 0.0010 - 247ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.1921 - val_loss: 0.0597 - lr: 0.0010 - 240ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.1433 - val_loss: 0.0629 - lr: 0.0010 - 226ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.1152 - val_loss: 0.0632 - lr: 1.0000e-04 - 238ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.1110 - val_loss: 0.0636 - lr: 1.0000e-04 - 264ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.1069 - val_loss: 0.0639 - lr: 1.0000e-04 - 262ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.1029 - val_loss: 0.0643 - lr: 1.0000e-04 - 250ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0989 - val_loss: 0.0646 - lr: 1.0000e-04 - 223ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0964 - val_loss: 0.0647 - lr: 1.0000e-05 - 244ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0960 - val_loss: 0.0647 - lr: 1.0000e-05 - 244ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0956 - val_loss: 0.0647 - lr: 1.0000e-05 - 250ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0952 - val_loss: 0.0648 - lr: 1.0000e-05 - 233ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0948 - val_loss: 0.0648 - lr: 1.0000e-05 - 251ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0944 - val_loss: 0.0649 - lr: 1.0000e-05 - 250ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0940 - val_loss: 0.0649 - lr: 1.0000e-05 - 258ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0936 - val_loss: 0.0649 - lr: 1.0000e-05 - 227ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0932 - val_loss: 0.0650 - lr: 1.0000e-05 - 245ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0928 - val_loss: 0.0650 - lr: 1.0000e-05 - 250ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0924 - val_loss: 0.0651 - lr: 1.0000e-05 - 263ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0920 - val_loss: 0.0651 - lr: 1.0000e-05 - 250ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0916 - val_loss: 0.0651 - lr: 1.0000e-05 - 246ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0912 - val_loss: 0.0652 - lr: 1.0000e-05 - 230ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0908 - val_loss: 0.0652 - lr: 1.0000e-05 - 283ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0904 - val_loss: 0.0653 - lr: 1.0000e-05 - 295ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0900 - val_loss: 0.0653 - lr: 1.0000e-05 - 252ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0896 - val_loss: 0.0654 - lr: 1.0000e-05 - 304ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0892 - val_loss: 0.0654 - lr: 1.0000e-05 - 218ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0888 - val_loss: 0.0654 - lr: 1.0000e-05 - 222ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0885 - val_loss: 0.0655 - lr: 1.0000e-05 - 231ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0881 - val_loss: 0.0655 - lr: 1.0000e-05 - 245ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0877 - val_loss: 0.0656 - lr: 1.0000e-05 - 257ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0873 - val_loss: 0.0656 - lr: 1.0000e-05 - 268ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0869 - val_loss: 0.0657 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0865 - val_loss: 0.0657 - lr: 1.0000e-05 - 269ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0861 - val_loss: 0.0658 - lr: 1.0000e-05 - 251ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0857 - val_loss: 0.0658 - lr: 1.0000e-05 - 242ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0853 - val_loss: 0.0659 - lr: 1.0000e-05 - 219ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0849 - val_loss: 0.0659 - lr: 1.0000e-05 - 254ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0845 - val_loss: 0.0659 - lr: 1.0000e-05 - 249ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0841 - val_loss: 0.0660 - lr: 1.0000e-05 - 248ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0837 - val_loss: 0.0660 - lr: 1.0000e-05 - 220ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0833 - val_loss: 0.0661 - lr: 1.0000e-05 - 264ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0829 - val_loss: 0.0661 - lr: 1.0000e-05 - 281ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0825 - val_loss: 0.0662 - lr: 1.0000e-05 - 241ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0821 - val_loss: 0.0662 - lr: 1.0000e-05 - 252ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0818 - val_loss: 0.0663 - lr: 1.0000e-05 - 273ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0814 - val_loss: 0.0663 - lr: 1.0000e-05 - 233ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04951
43/43 - 0s - loss: 1.0810 - val_loss: 0.0664 - lr: 1.0000e-05 - 246ms/epoch - 6ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 19.776724587061057 
RMSE:	 4.447102943159856 
MAPE:	 3.587879520041786

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	48.88% Accuracy
MSE:	 31.621751516368622 
RMSE:	 5.623322106759368 
MAPE:	 4.355106062590965

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 52.4753296205182 
RMSE:	 7.2439857551294375 
MAPE:	 5.852253139584933

DEMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 146.44755629127866 
RMSE:	 12.10155181335347 
MAPE:	 10.943210296434415

KAMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 19.64215945229788 
RMSE:	 4.4319475913302355 
MAPE:	 3.5686191181651687

MIDPOINT
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	45.52% Accuracy
MSE:	 19.83404242536117 
RMSE:	 4.453542682557468 
MAPE:	 3.5743844299716057

T3
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 70.66866288490243 
RMSE:	 8.406465540576637 
MAPE:	 6.802843731006552
TEMA
TEMA([input_arrays], [timeperiod=30])

Triple Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
9

Working on TEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=inf, Time=0.47 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=4352.703, Time=0.03 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=3889.412, Time=0.05 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=inf, Time=0.25 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=3689.930, Time=0.05 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=3574.245, Time=0.08 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=inf, Time=1.18 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=inf, Time=0.79 sec
 ARIMA(3,3,0)(0,0,0)[0] intercept   : AIC=3576.245, Time=0.18 sec

Best model:  ARIMA(3,3,0)(0,0,0)[0]          
Total fit time: 3.098 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 0)   Log Likelihood               -1783.123
Date:                Sun, 12 Dec 2021   AIC                           3574.245
Time:                        15:28:06   BIC                           3593.008
Sample:                             0   HQIC                          3581.451
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
ar.L1         -1.1480      0.004   -302.430      0.000      -1.155      -1.141
ar.L2         -0.8300      0.008    -99.682      0.000      -0.846      -0.814
ar.L3         -0.3687      0.007    -50.527      0.000      -0.383      -0.354
sigma2         4.9055      0.028    175.970      0.000       4.851       4.960
===================================================================================
Ljung-Box (L1) (Q):                  11.61   Jarque-Bera (JB):           1261976.58
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.16   Skew:                             2.52
Prob(H) (two-sided):                  0.00   Kurtosis:                       196.90
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
ARIMA order: (3, 3, 0) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04045, saving model to LSTM4.h5
90/90 - 4s - loss: 1.2159 - val_loss: 0.0404 - lr: 0.0010 - 4s/epoch - 47ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.9800 - val_loss: 0.0482 - lr: 0.0010 - 524ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.8617 - val_loss: 0.0639 - lr: 0.0010 - 443ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.8000 - val_loss: 0.0842 - lr: 0.0010 - 467ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.7583 - val_loss: 0.1038 - lr: 0.0010 - 502ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.7272 - val_loss: 0.1197 - lr: 0.0010 - 462ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.7111 - val_loss: 0.1210 - lr: 1.0000e-04 - 534ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.7087 - val_loss: 0.1224 - lr: 1.0000e-04 - 533ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.7062 - val_loss: 0.1238 - lr: 1.0000e-04 - 443ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.7037 - val_loss: 0.1251 - lr: 1.0000e-04 - 482ms/epoch - 5ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.7012 - val_loss: 0.1265 - lr: 1.0000e-04 - 447ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6996 - val_loss: 0.1266 - lr: 1.0000e-05 - 451ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6993 - val_loss: 0.1268 - lr: 1.0000e-05 - 479ms/epoch - 5ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6991 - val_loss: 0.1269 - lr: 1.0000e-05 - 437ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6988 - val_loss: 0.1271 - lr: 1.0000e-05 - 447ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6985 - val_loss: 0.1272 - lr: 1.0000e-05 - 584ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6982 - val_loss: 0.1274 - lr: 1.0000e-05 - 449ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6979 - val_loss: 0.1276 - lr: 1.0000e-05 - 440ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6976 - val_loss: 0.1277 - lr: 1.0000e-05 - 548ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6974 - val_loss: 0.1279 - lr: 1.0000e-05 - 516ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6971 - val_loss: 0.1281 - lr: 1.0000e-05 - 504ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6967 - val_loss: 0.1282 - lr: 1.0000e-05 - 515ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6964 - val_loss: 0.1284 - lr: 1.0000e-05 - 457ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6961 - val_loss: 0.1286 - lr: 1.0000e-05 - 534ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6958 - val_loss: 0.1288 - lr: 1.0000e-05 - 475ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6955 - val_loss: 0.1290 - lr: 1.0000e-05 - 459ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6952 - val_loss: 0.1291 - lr: 1.0000e-05 - 488ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6949 - val_loss: 0.1293 - lr: 1.0000e-05 - 480ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6946 - val_loss: 0.1295 - lr: 1.0000e-05 - 568ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6942 - val_loss: 0.1297 - lr: 1.0000e-05 - 560ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6939 - val_loss: 0.1299 - lr: 1.0000e-05 - 439ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6936 - val_loss: 0.1301 - lr: 1.0000e-05 - 527ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6933 - val_loss: 0.1303 - lr: 1.0000e-05 - 483ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6929 - val_loss: 0.1305 - lr: 1.0000e-05 - 445ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6926 - val_loss: 0.1307 - lr: 1.0000e-05 - 471ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6923 - val_loss: 0.1309 - lr: 1.0000e-05 - 427ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6920 - val_loss: 0.1311 - lr: 1.0000e-05 - 481ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6916 - val_loss: 0.1313 - lr: 1.0000e-05 - 415ms/epoch - 5ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6913 - val_loss: 0.1315 - lr: 1.0000e-05 - 481ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6910 - val_loss: 0.1317 - lr: 1.0000e-05 - 424ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6907 - val_loss: 0.1319 - lr: 1.0000e-05 - 533ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6903 - val_loss: 0.1321 - lr: 1.0000e-05 - 433ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6900 - val_loss: 0.1323 - lr: 1.0000e-05 - 525ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6897 - val_loss: 0.1324 - lr: 1.0000e-05 - 467ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6893 - val_loss: 0.1326 - lr: 1.0000e-05 - 469ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6890 - val_loss: 0.1328 - lr: 1.0000e-05 - 442ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6887 - val_loss: 0.1330 - lr: 1.0000e-05 - 520ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6883 - val_loss: 0.1332 - lr: 1.0000e-05 - 460ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6880 - val_loss: 0.1334 - lr: 1.0000e-05 - 461ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04045
90/90 - 0s - loss: 0.6877 - val_loss: 0.1336 - lr: 1.0000e-05 - 421ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04045
90/90 - 1s - loss: 0.6874 - val_loss: 0.1338 - lr: 1.0000e-05 - 540ms/epoch - 6ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 19.776724587061057 
RMSE:	 4.447102943159856 
MAPE:	 3.587879520041786

EMA
Prediction vs Close:		57.09% Accuracy
Prediction vs Prediction:	48.88% Accuracy
MSE:	 31.621751516368622 
RMSE:	 5.623322106759368 
MAPE:	 4.355106062590965

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 52.4753296205182 
RMSE:	 7.2439857551294375 
MAPE:	 5.852253139584933

DEMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 146.44755629127866 
RMSE:	 12.10155181335347 
MAPE:	 10.943210296434415

KAMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 19.64215945229788 
RMSE:	 4.4319475913302355 
MAPE:	 3.5686191181651687

MIDPOINT
Prediction vs Close:		49.63% Accuracy
Prediction vs Prediction:	45.52% Accuracy
MSE:	 19.83404242536117 
RMSE:	 4.453542682557468 
MAPE:	 3.5743844299716057

T3
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 70.66866288490243 
RMSE:	 8.406465540576637 
MAPE:	 6.802843731006552

TEMA
Prediction vs Close:		51.12% Accuracy
Prediction vs Prediction:	48.88% Accuracy
MSE:	 14.860699364166678 
RMSE:	 3.8549577642519868 
MAPE:	 3.1502795604602833
Runtime: mins: 11.725093292033337

Architecture Used¶

from google.colab import files
import cv2
uploaded = files.upload()

img = cv2.imread('Experiment4.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)

<matplotlib.image.AxesImage at 0x7fa5ea202a50>

Model Plots¶

for i in range(len(list(simulation4.keys()))):
  SIM = list(simulation4.keys())[i]
  plot_train(simulation4,SIM)
  plot_test(simulation4,SIM)

----- Train RMSE for SMA ----- 2.7003156237977874
----- Train_MSE_LSTM for SMA ----- 7.291704468126434
----- Train MAE LSTM for SMA ----- 2.660792327163243

----- Test RMSE for SMA----- 4.447102943159856
----- Test_MSE_LSTM for SMA----- 19.776724587061057
----- Test_MAE_LSTM for SMA----- 3.587879520041786

----- Train RMSE for EMA ----- 1.713593446317321
----- Train_MSE_LSTM for EMA ----- 2.9364024992616735
----- Train MAE LSTM for EMA ----- 1.5223039660123314

----- Test RMSE for EMA----- 5.623322106759368
----- Test_MSE_LSTM for EMA----- 31.621751516368622
----- Test_MAE_LSTM for EMA----- 4.355106062590965

----- Train RMSE for WMA ----- 3.927450398854089
----- Train_MSE_LSTM for WMA ----- 15.424866635459145
----- Train MAE LSTM for WMA ----- 3.865711769255081

----- Test RMSE for WMA----- 7.2439857551294375
----- Test_MSE_LSTM for WMA----- 52.4753296205182
----- Test_MAE_LSTM for WMA----- 5.852253139584933

----- Train RMSE for DEMA ----- 2.0481672182170936
----- Train_MSE_LSTM for DEMA ----- 4.194988953779147
----- Train MAE LSTM for DEMA ----- 1.7103755544907977

----- Test RMSE for DEMA----- 12.10155181335347
----- Test_MSE_LSTM for DEMA----- 146.44755629127866
----- Test_MAE_LSTM for DEMA----- 10.943210296434415

----- Train RMSE for KAMA ----- 4.06602280300264
----- Train_MSE_LSTM for KAMA ----- 16.532541434537443
----- Train MAE LSTM for KAMA ----- 4.004387627733816

----- Test RMSE for KAMA----- 4.4319475913302355
----- Test_MSE_LSTM for KAMA----- 19.64215945229788
----- Test_MAE_LSTM for KAMA----- 3.5686191181651687

Arima w Exogenous Variable Multistep MutiVariate LSTM Hybrid Model Experiment 5¶

def get_arima_exog(dataframe,original_data, train_len, test_len):    
    

    # prepare train and test data for exogenous vr
    X_value = pd.DataFrame(low_vol.iloc[:, :])
    y_value = pd.DataFrame(low_vol.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    X_scale_dataset = X_scaler.fit_transform(X_value)
    y_scale_dataset = y_scaler.fit_transform(y_value)
    # Get data and check shape
    # X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X_scale_dataset)
    y_train, y_test, = split_train_test(y_scale_dataset)
    yc_train,yc_test = split_train_test(low_vol_data)
    yc = yc_test.values.tolist()
    y_train_list = y_train.flatten().tolist()
    y_test_list = y_test.flatten().tolist()
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)

    # Initialize model
    model = auto_arima(y_train_list,exogenous  = X_train,trace=True, error_action='ignore', start_p=1,start_q=1,max_p=3,max_q=3,d=3,
            suppress_warnings=True,stepwise=True,seasonal=True)

      # Determine model parameters
    print(model.summary())
    model.fit(y_train_list,maxiter=200)
    order = model.get_params()['order']
    print('ARIMA order:', order, '\n')

      # Genereate predictions
    prediction = []
    for i in range(len(y_test_list)):
        model = pmdarima.ARIMA(order=order)
        model.fit(y_train_list)
        # print('working on', i+1, 'of', len(y_test), '-- ' + str(int(100 * (i + 1) / len(y_test))) + '% complete')

        prediction.append(model.predict()[0])
        y_train_list.append(y_test_list[i])

    predictionte = y_scaler.inverse_transform(np.array(prediction).reshape(-1,1))
    y_test_ = y_scaler.inverse_transform(np.array(y_test_list).reshape(-1,1))

    # Generate error data
    mse = mean_squared_error(yc_test, predictionte)
    rmse = mse ** 0.5
    mae = mean_absolute_error(y_test_ , predictionte )
    return yc,predictionte.flatten().tolist(), mse, rmse, mae

def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det = 20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # Option 1
    # Set up & fit LSTM RNN
    model = Sequential()
    model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    model.add(Dense(units=64,activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(units=output_dim))
    model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    ## Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM5.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()


    # # option 2
    # model = Sequential()
    # model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    # model.add(Dense(64))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 3
    # define custom activation
    # reference: https://github.com/Vaibhav-Sachdeva/Correlation-Coefficient-Prediction-using-ARIMA-LSTM-Hybrid-Model/blob/main/Code/LSTM-ARIMA.ipynb
    # class Double_Tanh(Activation):
    #     def __init__(self, activation, **kwargs):
    #         super(Double_Tanh, self).__init__(activation, **kwargs)
    #         self.__name__ = 'double_tanh'

    # def double_tanh(x):
    #     return (K.tanh(x) * 2)

    # get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
    #     # Model Generation
    # model = Sequential()
    # #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    # model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    # model.add(Dense(1))
    # model.add(Activation(double_tanh))
    # model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(input_dim, feature_size)))
    # model.add(LSTM(units=int(lstm_len/2)))
    # model.add(Dense(1, activation='sigmoid'))
    # model.compile(loss='mean_squared_error', optimizer='adam')
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM5.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te

if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation5 = {}
    imgfile = 'Experiment5'
    for ma in optimized_period:
                print(ma)
                print(functions[ma])
                print ( int( optimized_period[ma]))
              # if ma == 'SMA':
                low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
                low_vol = low_vol.fillna(0)
                low_vol_data = df['close']
                high_vol = pd.DataFrame()
                df2 = df.copy()
                for i in df2.columns:
                  if i in low_vol.columns:
                    high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
                high_vol_data = df['close']
                ## *****************************************************
                # Generate ARIMA and LSTM predictions
                print('\nWorking on ' + ma + ' predictions')
                try:
                  print('parameters used : ', train_len, test_len)
                  low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima_exog(low_vol,low_vol_data, train_len, test_len)
                except:
                    print('ARIMA error, skipping to next MA type')
                    continue
                Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
                final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
                mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
                rmse_ftr = mse_ftr ** 0.5
                mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
                mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

                final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
                mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
                rmse = mse ** 0.5
                mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                # Generate prediction accuracy
                actual = df['close'].tail(test_len).values
                result_1 = []
                result_2 = []
                for i in range(1, len(final_prediction)):
                    # Compare prediction to previous close price
                    if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                        result_1.append(1)
                    elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                        result_1.append(1)
                    else:
                        result_1.append(0)

                    # Compare prediction to previous prediction
                    if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                        result_2.append(1)
                    elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                        result_2.append(1)
                    else:
                        result_2.append(0)

                accuracy_1 = np.mean(result_1)
                accuracy_2 = np.mean(result_2)

                simulation5[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                              'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                  'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                              'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                  'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                              'rmse': rmse_ftr, 'mae' : mae_ftr},
                                  'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                            'rmse': rmse, 'mae': mae },
                                  'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

                # save simulation data here as checkpoint
                with open('simulation5_data.json', 'w') as fp:
                    json.dump(simulation5, fp)

                for ma in simulation5.keys():
                    print('\n' + ma)
                    print('Prediction vs Close:\t\t' + str(round(100*simulation5[ma]['accuracy']['prediction vs close'], 2))
                          + '% Accuracy')
                    print('Prediction vs Prediction:\t' + str(round(100*simulation5[ma]['accuracy']['prediction vs prediction'], 2))
                          + '% Accuracy')
                    print('MSE:\t', simulation5[ma]['final']['mse'],
                          '\nRMSE:\t', simulation5[ma]['final']['rmse'],
                          '\nMAPE:\t', simulation5[ma]['final']['mae'])#,
                          # '\nMAPE:\t', simulation[ma]['final']['mape'])
              # else:
              #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.787, Time=3.85 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.588, Time=5.46 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-14596.280, Time=5.73 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.588, Time=8.46 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16924.805, Time=10.67 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-14482.349, Time=10.95 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-17215.608, Time=21.20 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-14552.588, Time=10.42 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-15570.350, Time=19.26 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-11671.292, Time=27.08 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 123.097 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8639.804
Date:                Sun, 12 Dec 2021   AIC                         -17215.608
Time:                        16:07:33   BIC                         -17065.501
Sample:                             0   HQIC                        -17157.961
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -4.057e-09   5.82e-05  -6.97e-05      1.000      -0.000       0.000
x2         -4.057e-09   5.81e-05  -6.99e-05      1.000      -0.000       0.000
x3         -4.111e-09   5.49e-05  -7.49e-05      1.000      -0.000       0.000
x4             1.0000   5.71e-05   1.75e+04      0.000       1.000       1.000
x5         -3.706e-09   5.43e-05  -6.82e-05      1.000      -0.000       0.000
x6         -1.082e-08      0.000  -6.08e-05      1.000      -0.000       0.000
x7         -4.025e-09   5.63e-05  -7.15e-05      1.000      -0.000       0.000
x8         -4.035e-09   5.19e-05  -7.78e-05      1.000      -0.000       0.000
x9         -1.522e-10    2.9e-05  -5.25e-06      1.000   -5.68e-05    5.68e-05
x10        -6.396e-10   1.04e-05  -6.15e-05      1.000   -2.04e-05    2.04e-05
x11        -3.921e-09   5.06e-05  -7.75e-05      1.000   -9.91e-05    9.91e-05
x12        -4.102e-09   5.29e-05  -7.76e-05      1.000      -0.000       0.000
x13        -4.087e-09   5.75e-05  -7.11e-05      1.000      -0.000       0.000
x14        -3.619e-08      0.000     -0.000      1.000      -0.000       0.000
x15        -4.806e-09   4.61e-05     -0.000      1.000   -9.03e-05    9.03e-05
x16        -3.507e-09      0.000  -2.98e-05      1.000      -0.000       0.000
x17        -3.121e-09   6.02e-05  -5.18e-05      1.000      -0.000       0.000
x18        -1.172e-08      0.000     -0.000      1.000      -0.000       0.000
x19        -5.433e-09   6.06e-05  -8.96e-05      1.000      -0.000       0.000
x20        -1.393e-08   4.79e-05     -0.000      1.000   -9.39e-05    9.39e-05
x21        -4.216e-09   6.63e-05  -6.36e-05      1.000      -0.000       0.000
x22        -3.479e-11   1.66e-08     -0.002      0.998   -3.25e-08    3.24e-08
x23        -9.221e-10    1.4e-07     -0.007      0.995   -2.74e-07    2.73e-07
x24        -8.085e-08      0.001  -6.96e-05      1.000      -0.002       0.002
x25        -9.642e-08      0.001     -0.000      1.000      -0.002       0.002
x26        -5.019e-08      0.000     -0.000      1.000      -0.000       0.000
x27        -2.457e-08   7.65e-05     -0.000      1.000      -0.000       0.000
x28        -3.411e-08      0.000     -0.000      1.000      -0.000       0.000
x29        -1.507e-08   4.36e-05     -0.000      1.000   -8.54e-05    8.54e-05
ma.L1         -1.3898   8.03e-07  -1.73e+06      0.000      -1.390      -1.390
ma.L2          0.4031   8.36e-07   4.82e+05      0.000       0.403       0.403
sigma2      7.528e-11   7.24e-11      1.040      0.298   -6.66e-11    2.17e-10
===================================================================================
Ljung-Box (L1) (Q):                  89.12   Jarque-Bera (JB):           1533103.33
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             5.56
Prob(H) (two-sided):                  0.00   Kurtosis:                       216.50
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.08e+25. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 

WARNING:tensorflow:Layer lstm_57 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_57 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.25612, saving model to LSTM5.h5
48/48 - 2s - loss: 0.4353 - val_loss: 0.2561 - lr: 0.0010 - 2s/epoch - 39ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.25612 to 0.11825, saving model to LSTM5.h5
48/48 - 0s - loss: 0.1198 - val_loss: 0.1182 - lr: 0.0010 - 456ms/epoch - 9ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.11825 to 0.11433, saving model to LSTM5.h5
48/48 - 0s - loss: 0.0779 - val_loss: 0.1143 - lr: 0.0010 - 432ms/epoch - 9ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.11433
48/48 - 0s - loss: 0.0580 - val_loss: 0.1983 - lr: 0.0010 - 402ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.11433 to 0.02870, saving model to LSTM5.h5
48/48 - 0s - loss: 0.0636 - val_loss: 0.0287 - lr: 0.0010 - 499ms/epoch - 10ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0631 - val_loss: 0.5273 - lr: 0.0010 - 422ms/epoch - 9ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0476 - val_loss: 0.2411 - lr: 0.0010 - 411ms/epoch - 9ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0466 - val_loss: 0.1020 - lr: 0.0010 - 412ms/epoch - 9ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0515 - val_loss: 0.4444 - lr: 0.0010 - 408ms/epoch - 8ms/step
Epoch 10/500

Epoch 00010: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00010: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0405 - val_loss: 0.2259 - lr: 0.0010 - 417ms/epoch - 9ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0415 - val_loss: 0.2207 - lr: 1.0000e-04 - 379ms/epoch - 8ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0369 - val_loss: 0.2140 - lr: 1.0000e-04 - 466ms/epoch - 10ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0336 - val_loss: 0.2095 - lr: 1.0000e-04 - 387ms/epoch - 8ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0392 - val_loss: 0.2049 - lr: 1.0000e-04 - 417ms/epoch - 9ms/step
Epoch 15/500

Epoch 00015: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00015: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0362 - val_loss: 0.1977 - lr: 1.0000e-04 - 406ms/epoch - 8ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0357 - val_loss: 0.1975 - lr: 1.0000e-05 - 377ms/epoch - 8ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0379 - val_loss: 0.1971 - lr: 1.0000e-05 - 407ms/epoch - 8ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0373 - val_loss: 0.1969 - lr: 1.0000e-05 - 409ms/epoch - 9ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0379 - val_loss: 0.1965 - lr: 1.0000e-05 - 446ms/epoch - 9ms/step
Epoch 20/500

Epoch 00020: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00020: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0361 - val_loss: 0.1961 - lr: 1.0000e-05 - 406ms/epoch - 8ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0378 - val_loss: 0.1957 - lr: 1.0000e-05 - 415ms/epoch - 9ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0350 - val_loss: 0.1953 - lr: 1.0000e-05 - 437ms/epoch - 9ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0357 - val_loss: 0.1945 - lr: 1.0000e-05 - 426ms/epoch - 9ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0379 - val_loss: 0.1938 - lr: 1.0000e-05 - 401ms/epoch - 8ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0388 - val_loss: 0.1927 - lr: 1.0000e-05 - 378ms/epoch - 8ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0341 - val_loss: 0.1916 - lr: 1.0000e-05 - 385ms/epoch - 8ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0353 - val_loss: 0.1913 - lr: 1.0000e-05 - 393ms/epoch - 8ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0389 - val_loss: 0.1907 - lr: 1.0000e-05 - 400ms/epoch - 8ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0335 - val_loss: 0.1898 - lr: 1.0000e-05 - 405ms/epoch - 8ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0348 - val_loss: 0.1892 - lr: 1.0000e-05 - 442ms/epoch - 9ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0362 - val_loss: 0.1879 - lr: 1.0000e-05 - 386ms/epoch - 8ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0377 - val_loss: 0.1861 - lr: 1.0000e-05 - 372ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0366 - val_loss: 0.1856 - lr: 1.0000e-05 - 421ms/epoch - 9ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0359 - val_loss: 0.1856 - lr: 1.0000e-05 - 417ms/epoch - 9ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0345 - val_loss: 0.1849 - lr: 1.0000e-05 - 390ms/epoch - 8ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0315 - val_loss: 0.1843 - lr: 1.0000e-05 - 405ms/epoch - 8ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0351 - val_loss: 0.1835 - lr: 1.0000e-05 - 379ms/epoch - 8ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0342 - val_loss: 0.1831 - lr: 1.0000e-05 - 407ms/epoch - 8ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0343 - val_loss: 0.1819 - lr: 1.0000e-05 - 481ms/epoch - 10ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0327 - val_loss: 0.1816 - lr: 1.0000e-05 - 379ms/epoch - 8ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0316 - val_loss: 0.1806 - lr: 1.0000e-05 - 417ms/epoch - 9ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0349 - val_loss: 0.1790 - lr: 1.0000e-05 - 432ms/epoch - 9ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0354 - val_loss: 0.1780 - lr: 1.0000e-05 - 416ms/epoch - 9ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0307 - val_loss: 0.1776 - lr: 1.0000e-05 - 458ms/epoch - 10ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0325 - val_loss: 0.1778 - lr: 1.0000e-05 - 490ms/epoch - 10ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0364 - val_loss: 0.1772 - lr: 1.0000e-05 - 398ms/epoch - 8ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0339 - val_loss: 0.1769 - lr: 1.0000e-05 - 464ms/epoch - 10ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0331 - val_loss: 0.1767 - lr: 1.0000e-05 - 430ms/epoch - 9ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0326 - val_loss: 0.1763 - lr: 1.0000e-05 - 376ms/epoch - 8ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0328 - val_loss: 0.1755 - lr: 1.0000e-05 - 381ms/epoch - 8ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0352 - val_loss: 0.1756 - lr: 1.0000e-05 - 411ms/epoch - 9ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0312 - val_loss: 0.1758 - lr: 1.0000e-05 - 372ms/epoch - 8ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0327 - val_loss: 0.1758 - lr: 1.0000e-05 - 398ms/epoch - 8ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0343 - val_loss: 0.1750 - lr: 1.0000e-05 - 421ms/epoch - 9ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.02870
48/48 - 0s - loss: 0.0307 - val_loss: 0.1742 - lr: 1.0000e-05 - 416ms/epoch - 9ms/step
Epoch 00055: early stopping

SMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	52.61% Accuracy
MSE:	 34.39169744803393 
RMSE:	 5.864443490053761 
MAPE:	 4.893666026892695
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.778, Time=3.79 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.587, Time=5.47 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15952.568, Time=15.15 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.587, Time=7.81 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16628.634, Time=10.62 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-16462.206, Time=24.29 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16848.298, Time=12.82 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17014.023, Time=6.57 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-16988.619, Time=3.78 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17071.454, Time=7.45 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=inf, Time=18.63 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-16987.994, Time=3.86 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-16982.667, Time=5.19 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 125.475 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8569.727
Date:                Sun, 12 Dec 2021   AIC                         -17071.454
Time:                        16:13:56   BIC                         -16911.966
Sample:                             0   HQIC                        -17010.204
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -2.316e-10   6.25e-05  -3.71e-06      1.000      -0.000       0.000
x2         -2.309e-10   6.24e-05   -3.7e-06      1.000      -0.000       0.000
x3         -2.325e-10   6.26e-05  -3.71e-06      1.000      -0.000       0.000
x4             1.0000   6.25e-05    1.6e+04      0.000       1.000       1.000
x5         -2.107e-10   5.96e-05  -3.54e-06      1.000      -0.000       0.000
x6         -7.997e-10      0.000  -7.41e-06      1.000      -0.000       0.000
x7         -2.295e-10   6.22e-05  -3.69e-06      1.000      -0.000       0.000
x8         -2.246e-10   6.15e-05  -3.65e-06      1.000      -0.000       0.000
x9         -1.167e-11   1.25e-05  -9.33e-07      1.000   -2.45e-05    2.45e-05
x10        -4.454e-11   2.66e-05  -1.68e-06      1.000   -5.21e-05    5.21e-05
x11        -2.221e-10   6.11e-05  -3.63e-06      1.000      -0.000       0.000
x12        -2.266e-10   6.18e-05  -3.66e-06      1.000      -0.000       0.000
x13        -2.315e-10   6.25e-05  -3.71e-06      1.000      -0.000       0.000
x14        -1.767e-09      0.000  -1.02e-05      1.000      -0.000       0.000
x15         -2.11e-10   5.93e-05  -3.56e-06      1.000      -0.000       0.000
x16        -5.283e-10   9.45e-05  -5.59e-06      1.000      -0.000       0.000
x17        -2.098e-10   6.01e-05  -3.49e-06      1.000      -0.000       0.000
x18         -3.82e-11   2.41e-05  -1.58e-06      1.000   -4.73e-05    4.73e-05
x19        -2.645e-10   6.61e-05     -4e-06      1.000      -0.000       0.000
x20        -2.417e-10   6.21e-05  -3.89e-06      1.000      -0.000       0.000
x21        -4.824e-10   8.83e-05  -5.46e-06      1.000      -0.000       0.000
x22        -3.758e-13   1.19e-11     -0.032      0.975   -2.36e-11    2.29e-11
x23        -1.089e-11   8.42e-11     -0.129      0.897   -1.76e-10    1.54e-10
x24        -2.538e-09      0.000  -1.44e-05      1.000      -0.000       0.000
x25        -2.038e-09      0.000  -1.49e-05      1.000      -0.000       0.000
x26         -3.16e-09      0.000  -1.37e-05      1.000      -0.000       0.000
x27        -2.955e-09      0.000  -1.32e-05      1.000      -0.000       0.000
x28        -1.664e-09      0.000  -9.94e-06      1.000      -0.000       0.000
x29        -1.568e-09      0.000  -9.63e-06      1.000      -0.000       0.000
ar.L1         -0.4923    6.2e-10  -7.94e+08      0.000      -0.492      -0.492
ar.L2         -0.1923    3.6e-10  -5.35e+08      0.000      -0.192      -0.192
ar.L3         -0.0462   1.71e-10  -2.71e+08      0.000      -0.046      -0.046
ma.L1         -0.7077   1.41e-09  -5.04e+08      0.000      -0.708      -0.708
sigma2       8.99e-11   6.96e-11      1.291      0.197   -4.66e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  51.79   Jarque-Bera (JB):           4012066.18
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.44
Prob(H) (two-sided):                  0.00   Kurtosis:                       348.68
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 5.01e+30. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 

WARNING:tensorflow:Layer lstm_58 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_58 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.35754, saving model to LSTM5.h5
16/16 - 2s - loss: 0.7057 - val_loss: 0.3575 - lr: 0.0010 - 2s/epoch - 95ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.35754 to 0.02747, saving model to LSTM5.h5
16/16 - 0s - loss: 0.2192 - val_loss: 0.0275 - lr: 0.0010 - 160ms/epoch - 10ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.02747
16/16 - 0s - loss: 0.1892 - val_loss: 0.0299 - lr: 0.0010 - 166ms/epoch - 10ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.02747
16/16 - 0s - loss: 0.0957 - val_loss: 0.0364 - lr: 0.0010 - 150ms/epoch - 9ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.02747 to 0.01373, saving model to LSTM5.h5
16/16 - 0s - loss: 0.0562 - val_loss: 0.0137 - lr: 0.0010 - 162ms/epoch - 10ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.01373
16/16 - 0s - loss: 0.0545 - val_loss: 0.0143 - lr: 0.0010 - 146ms/epoch - 9ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.01373 to 0.01201, saving model to LSTM5.h5
16/16 - 0s - loss: 0.0451 - val_loss: 0.0120 - lr: 0.0010 - 177ms/epoch - 11ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.01201
16/16 - 0s - loss: 0.0470 - val_loss: 0.0320 - lr: 0.0010 - 147ms/epoch - 9ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.01201 to 0.00908, saving model to LSTM5.h5
16/16 - 0s - loss: 0.0439 - val_loss: 0.0091 - lr: 0.0010 - 173ms/epoch - 11ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0421 - val_loss: 0.0262 - lr: 0.0010 - 143ms/epoch - 9ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0416 - val_loss: 0.0110 - lr: 0.0010 - 149ms/epoch - 9ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0365 - val_loss: 0.0158 - lr: 0.0010 - 149ms/epoch - 9ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0391 - val_loss: 0.0105 - lr: 0.0010 - 148ms/epoch - 9ms/step
Epoch 14/500

Epoch 00014: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00014: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0346 - val_loss: 0.0095 - lr: 0.0010 - 143ms/epoch - 9ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0378 - val_loss: 0.0097 - lr: 1.0000e-04 - 146ms/epoch - 9ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0320 - val_loss: 0.0102 - lr: 1.0000e-04 - 145ms/epoch - 9ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0342 - val_loss: 0.0102 - lr: 1.0000e-04 - 157ms/epoch - 10ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0342 - val_loss: 0.0110 - lr: 1.0000e-04 - 138ms/epoch - 9ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00019: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0345 - val_loss: 0.0105 - lr: 1.0000e-04 - 143ms/epoch - 9ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0313 - val_loss: 0.0105 - lr: 1.0000e-05 - 146ms/epoch - 9ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0304 - val_loss: 0.0105 - lr: 1.0000e-05 - 152ms/epoch - 10ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0321 - val_loss: 0.0107 - lr: 1.0000e-05 - 148ms/epoch - 9ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0328 - val_loss: 0.0107 - lr: 1.0000e-05 - 152ms/epoch - 9ms/step
Epoch 24/500

Epoch 00024: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00024: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0327 - val_loss: 0.0107 - lr: 1.0000e-05 - 163ms/epoch - 10ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0313 - val_loss: 0.0107 - lr: 1.0000e-05 - 141ms/epoch - 9ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0352 - val_loss: 0.0107 - lr: 1.0000e-05 - 141ms/epoch - 9ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0320 - val_loss: 0.0107 - lr: 1.0000e-05 - 140ms/epoch - 9ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0335 - val_loss: 0.0107 - lr: 1.0000e-05 - 147ms/epoch - 9ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0324 - val_loss: 0.0106 - lr: 1.0000e-05 - 143ms/epoch - 9ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0315 - val_loss: 0.0106 - lr: 1.0000e-05 - 150ms/epoch - 9ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0324 - val_loss: 0.0106 - lr: 1.0000e-05 - 156ms/epoch - 10ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0337 - val_loss: 0.0106 - lr: 1.0000e-05 - 141ms/epoch - 9ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0308 - val_loss: 0.0104 - lr: 1.0000e-05 - 153ms/epoch - 10ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0324 - val_loss: 0.0104 - lr: 1.0000e-05 - 152ms/epoch - 9ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0318 - val_loss: 0.0104 - lr: 1.0000e-05 - 135ms/epoch - 8ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0299 - val_loss: 0.0104 - lr: 1.0000e-05 - 145ms/epoch - 9ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0321 - val_loss: 0.0104 - lr: 1.0000e-05 - 145ms/epoch - 9ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0326 - val_loss: 0.0105 - lr: 1.0000e-05 - 154ms/epoch - 10ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0305 - val_loss: 0.0105 - lr: 1.0000e-05 - 149ms/epoch - 9ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0315 - val_loss: 0.0104 - lr: 1.0000e-05 - 153ms/epoch - 10ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0351 - val_loss: 0.0105 - lr: 1.0000e-05 - 156ms/epoch - 10ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0330 - val_loss: 0.0106 - lr: 1.0000e-05 - 149ms/epoch - 9ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0320 - val_loss: 0.0105 - lr: 1.0000e-05 - 147ms/epoch - 9ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0327 - val_loss: 0.0104 - lr: 1.0000e-05 - 153ms/epoch - 10ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0304 - val_loss: 0.0105 - lr: 1.0000e-05 - 149ms/epoch - 9ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0328 - val_loss: 0.0106 - lr: 1.0000e-05 - 186ms/epoch - 12ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0320 - val_loss: 0.0106 - lr: 1.0000e-05 - 146ms/epoch - 9ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0289 - val_loss: 0.0106 - lr: 1.0000e-05 - 149ms/epoch - 9ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0319 - val_loss: 0.0106 - lr: 1.0000e-05 - 138ms/epoch - 9ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0338 - val_loss: 0.0105 - lr: 1.0000e-05 - 149ms/epoch - 9ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0309 - val_loss: 0.0106 - lr: 1.0000e-05 - 152ms/epoch - 10ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0331 - val_loss: 0.0105 - lr: 1.0000e-05 - 150ms/epoch - 9ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0334 - val_loss: 0.0106 - lr: 1.0000e-05 - 146ms/epoch - 9ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0326 - val_loss: 0.0105 - lr: 1.0000e-05 - 137ms/epoch - 9ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0310 - val_loss: 0.0104 - lr: 1.0000e-05 - 142ms/epoch - 9ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0339 - val_loss: 0.0104 - lr: 1.0000e-05 - 147ms/epoch - 9ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0344 - val_loss: 0.0103 - lr: 1.0000e-05 - 161ms/epoch - 10ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0280 - val_loss: 0.0103 - lr: 1.0000e-05 - 148ms/epoch - 9ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00908
16/16 - 0s - loss: 0.0306 - val_loss: 0.0103 - lr: 1.0000e-05 - 182ms/epoch - 11ms/step
Epoch 00059: early stopping

SMA
Prediction vs Close:		51.87% Accuracy
Prediction vs Prediction:	52.61% Accuracy
MSE:	 34.39169744803393 
RMSE:	 5.864443490053761 
MAPE:	 4.893666026892695

EMA
Prediction vs Close:		53.73% Accuracy
Prediction vs Prediction:	47.39% Accuracy
MSE:	 73.04930062485933 
RMSE:	 8.546888359213506 
MAPE:	 6.613879572809731
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.778, Time=3.41 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.587, Time=5.42 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-14597.576, Time=5.58 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.587, Time=8.18 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15338.693, Time=11.30 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15153.472, Time=27.61 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-17112.658, Time=15.58 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-14552.587, Time=10.56 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-15106.216, Time=13.87 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-12251.715, Time=33.99 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 135.507 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8588.329
Date:                Sun, 12 Dec 2021   AIC                         -17112.658
Time:                        16:24:58   BIC                         -16962.551
Sample:                             0   HQIC                        -17055.011
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1          -4.53e-09   3.26e-06     -0.001      0.999   -6.39e-06    6.38e-06
x2         -4.512e-09   3.25e-06     -0.001      0.999   -6.38e-06    6.37e-06
x3         -4.538e-09   3.26e-06     -0.001      0.999    -6.4e-06    6.39e-06
x4             1.0000   3.26e-06   3.07e+05      0.000       1.000       1.000
x5         -4.105e-09   3.11e-06     -0.001      0.999    -6.1e-06    6.09e-06
x6         -1.488e-08   5.45e-06     -0.003      0.998   -1.07e-05    1.07e-05
x7         -4.481e-09   3.24e-06     -0.001      0.999   -6.36e-06    6.36e-06
x8         -4.365e-09    3.2e-06     -0.001      0.999   -6.29e-06    6.28e-06
x9         -4.628e-10   8.38e-07     -0.001      1.000   -1.64e-06    1.64e-06
x10        -7.326e-10    1.3e-06     -0.001      1.000   -2.55e-06    2.54e-06
x11        -4.347e-09    3.2e-06     -0.001      0.999   -6.27e-06    6.26e-06
x12        -4.345e-09    3.2e-06     -0.001      0.999   -6.27e-06    6.26e-06
x13         -4.52e-09   3.26e-06     -0.001      0.999   -6.39e-06    6.38e-06
x14        -3.586e-08      9e-06     -0.004      0.997   -1.77e-05    1.76e-05
x15        -3.757e-09   2.98e-06     -0.001      0.999   -5.84e-06    5.83e-06
x16         -1.24e-08   5.36e-06     -0.002      0.998   -1.05e-05    1.05e-05
x17        -4.515e-09   3.26e-06     -0.001      0.999    -6.4e-06    6.39e-06
x18        -2.632e-10   7.07e-07     -0.000      1.000   -1.39e-06    1.39e-06
x19        -4.642e-09    3.3e-06     -0.001      0.999   -6.47e-06    6.46e-06
x20        -3.919e-10   6.91e-07     -0.001      1.000   -1.36e-06    1.35e-06
x21         -7.69e-09   4.13e-06     -0.002      0.999   -8.11e-06    8.09e-06
x22        -6.998e-12   2.69e-13    -25.970      0.000   -7.53e-12   -6.47e-12
x23         -1.81e-10   2.22e-12    -81.582      0.000   -1.85e-10   -1.77e-10
x24        -4.955e-08    8.9e-06     -0.006      0.996   -1.75e-05    1.74e-05
x25        -4.901e-08    8.4e-06     -0.006      0.995   -1.65e-05    1.64e-05
x26        -6.446e-08    1.2e-05     -0.005      0.996   -2.37e-05    2.35e-05
x27         -5.73e-08   1.14e-05     -0.005      0.996   -2.24e-05    2.23e-05
x28        -2.997e-08   8.22e-06     -0.004      0.997   -1.61e-05    1.61e-05
x29        -3.486e-08   8.89e-06     -0.004      0.997   -1.75e-05    1.74e-05
ma.L1         -1.3902   3.62e-10  -3.84e+09      0.000      -1.390      -1.390
ma.L2          0.4033   3.72e-10   1.08e+09      0.000       0.403       0.403
sigma2      8.541e-11   6.95e-11      1.229      0.219   -5.08e-11    2.22e-10
===================================================================================
Ljung-Box (L1) (Q):                  66.92   Jarque-Bera (JB):           6039240.46
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                            12.14
Prob(H) (two-sided):                  0.00   Kurtosis:                       426.63
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.94e+30. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 

WARNING:tensorflow:Layer lstm_59 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

WARNING:tensorflow:Layer lstm_59 will not use cuDNN kernels since it doesn't meet the criteria. It will use a generic GPU kernel as fallback when running on GPU.

Architecture Used¶

from google.colab import files
import cv2
uploaded = files.upload()

Saving Experiment5.png to Experiment5 (1).png

img = cv2.imread('Experiment5.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)

<matplotlib.image.AxesImage at 0x7fa5ea16d7d0>

Model Plots¶

for i in range(len(list(simulation5.keys()))):
  SIM = list(simulation5.keys())[i]
  plot_train(simulation5,SIM)
  plot_test(simulation5,SIM)

----- Train RMSE for SMA ----- 7.636357212019493
----- Train_MSE_LSTM for SMA ----- 58.31395146956212
----- Train MAE LSTM for SMA ----- 6.563417649903971

----- Test RMSE for SMA----- 5.864443490053761
----- Test_MSE_LSTM for SMA----- 34.39169744803393
----- Test_MAE_LSTM for SMA----- 4.893666026892695

----- Train RMSE for EMA ----- 9.308960691198413
----- Train_MSE_LSTM for EMA ----- 86.65674915027724
----- Train MAE LSTM for EMA ----- 8.140100172619418

----- Test RMSE for EMA----- 8.546888359213506
----- Test_MSE_LSTM for EMA----- 73.04930062485933
----- Test_MAE_LSTM for EMA----- 6.613879572809731

----- Train RMSE for WMA ----- 9.79972862979708
----- Train_MSE_LSTM for WMA ----- 96.03468121766456
----- Train MAE LSTM for WMA ----- 8.675562439114087

----- Test RMSE for WMA----- 8.387715385039114
----- Test_MSE_LSTM for WMA----- 70.35376938042184
----- Test_MAE_LSTM for WMA----- 6.8547592718484545

----- Train RMSE for DEMA ----- 11.043189962759177
----- Train_MSE_LSTM for DEMA ----- 121.95204455358504
----- Train MAE LSTM for DEMA ----- 9.832117659380973

----- Test RMSE for DEMA----- 8.381384847505505
----- Test_MSE_LSTM for DEMA----- 70.24761196199488
----- Test_MAE_LSTM for DEMA----- 6.862692730259403

----- Train RMSE for KAMA ----- 9.344372249039948
----- Train_MSE_LSTM for KAMA ----- 87.3172927286279
----- Train MAE LSTM for KAMA ----- 8.318259338837343

----- Test RMSE for KAMA----- 5.1975067685677505
----- Test_MSE_LSTM for KAMA----- 27.01407660930758
----- Test_MAE_LSTM for KAMA----- 4.263533603346384

Arima w Exogenous Variable Multistep MutiVariate LSTM Hybrid Model Experiment 6¶

def get_arima_exog(dataframe,original_data, train_len, test_len):    
    

    # prepare train and test data for exogenous vr
    X_value = pd.DataFrame(low_vol.iloc[:, :])
    y_value = pd.DataFrame(low_vol.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    X_scale_dataset = X_scaler.fit_transform(X_value)
    y_scale_dataset = y_scaler.fit_transform(y_value)
    # Get data and check shape
    # X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X_scale_dataset)
    y_train, y_test, = split_train_test(y_scale_dataset)
    yc_train,yc_test = split_train_test(low_vol_data)
    yc = yc_test.values.tolist()
    y_train_list = y_train.flatten().tolist()
    y_test_list = y_test.flatten().tolist()
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)

    # Initialize model
    model = auto_arima(y_train_list,exogenous  = X_train,trace=True, error_action='ignore', start_p=1,start_q=1,max_p=3,max_q=3,d=3,
            suppress_warnings=True,stepwise=True,seasonal=True)

      # Determine model parameters
    print(model.summary())
    model.fit(y_train_list,maxiter=200)
    order = model.get_params()['order']
    print('ARIMA order:', order, '\n')

      # Genereate predictions
    prediction = []
    for i in range(len(y_test_list)):
        model = pmdarima.ARIMA(order=order)
        model.fit(y_train_list)
        # print('working on', i+1, 'of', len(y_test), '-- ' + str(int(100 * (i + 1) / len(y_test))) + '% complete')

        prediction.append(model.predict()[0])
        y_train_list.append(y_test_list[i])

    predictionte = y_scaler.inverse_transform(np.array(prediction).reshape(-1,1))
    y_test_ = y_scaler.inverse_transform(np.array(y_test_list).reshape(-1,1))

    # Generate error data
    mse = mean_squared_error(yc_test, predictionte)
    rmse = mse ** 0.5
    mae = mean_absolute_error(y_test_ , predictionte )
    return yc,predictionte.flatten().tolist(), mse, rmse, mae

def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det =20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # Option 1
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    # model.add(Dense(units=64,activation='relu'))
    # model.add(Dropout(0.5))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    # ## Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()


    # # option 2
    model = Sequential()
    model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    model.add(Dense(64))
    model.add(Dense(units=output_dim))
    model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM6.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()

    # Option 3
    # define custom activation
    # reference: https://github.com/Vaibhav-Sachdeva/Correlation-Coefficient-Prediction-using-ARIMA-LSTM-Hybrid-Model/blob/main/Code/LSTM-ARIMA.ipynb
    # class Double_Tanh(Activation):
    #     def __init__(self, activation, **kwargs):
    #         super(Double_Tanh, self).__init__(activation, **kwargs)
    #         self.__name__ = 'double_tanh'

    # def double_tanh(x):
    #     return (K.tanh(x) * 2)

    # get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
    #     # Model Generation
    # model = Sequential()
    # #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    # model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    # model.add(Dense(1))
    # model.add(Activation(double_tanh))
    # model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(x_train.shape[1], 1)))
    # model.add(LSTM(units=int(lstm_len/2)))
    # model.add(Dense(1, activation='sigmoid'))
    # model.compile(loss='mean_squared_error', optimizer='adam')
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te

if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation6 = {}
    imgfile = 'Experiment6'
    for ma in optimized_period:
                print(ma)
                print(functions[ma])
                print ( int( optimized_period[ma]))
              # if ma == 'SMA':
                low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
                low_vol = low_vol.fillna(0)
                low_vol_data = df['close']
                high_vol = pd.DataFrame()
                df2 = df.copy()
                for i in df2.columns:
                  if i in low_vol.columns:
                    high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
                high_vol_data = df['close']
                ## *****************************************************
                # Generate ARIMA and LSTM predictions
                print('\nWorking on ' + ma + ' predictions')
                try:
                  print('parameters used : ', train_len, test_len)
                  low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima_exog(low_vol,low_vol_data, train_len, test_len)
                except:
                    print('ARIMA error, skipping to next MA type')
                    continue
                Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
                final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
                mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
                rmse_ftr = mse_ftr ** 0.5
                mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
                mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

                final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
                mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
                rmse = mse ** 0.5
                mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                # Generate prediction accuracy
                actual = df['close'].tail(test_len).values
                result_1 = []
                result_2 = []
                for i in range(1, len(final_prediction)):
                    # Compare prediction to previous close price
                    if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                        result_1.append(1)
                    elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                        result_1.append(1)
                    else:
                        result_1.append(0)

                    # Compare prediction to previous prediction
                    if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                        result_2.append(1)
                    elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                        result_2.append(1)
                    else:
                        result_2.append(0)

                accuracy_1 = np.mean(result_1)
                accuracy_2 = np.mean(result_2)

                simulation6[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                              'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                  'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                              'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                  'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                              'rmse': rmse_ftr, 'mae' : mae_ftr},
                                  'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                            'rmse': rmse, 'mae': mae },
                                  'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

                # save simulation data here as checkpoint
                with open('simulation6_data.json', 'w') as fp:
                    json.dump(simulation6, fp)

                for ma in simulation6.keys():
                    print('\n' + ma)
                    print('Prediction vs Close:\t\t' + str(round(100*simulation6[ma]['accuracy']['prediction vs close'], 2))
                          + '% Accuracy')
                    print('Prediction vs Prediction:\t' + str(round(100*simulation6[ma]['accuracy']['prediction vs prediction'], 2))
                          + '% Accuracy')
                    print('MSE:\t', simulation6[ma]['final']['mse'],
                          '\nRMSE:\t', simulation6[ma]['final']['rmse'],
                          '\nMAPE:\t', simulation6[ma]['final']['mae'])#,
                          # '\nMAPE:\t', simulation[ma]['final']['mape'])
              # else:
              #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.787, Time=3.67 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.588, Time=5.52 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-14596.280, Time=5.65 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.588, Time=8.39 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16924.805, Time=10.47 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-14482.349, Time=11.23 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-17215.608, Time=20.61 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-14552.588, Time=10.76 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-15570.350, Time=19.25 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-11671.292, Time=28.75 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 124.319 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8639.804
Date:                Sun, 12 Dec 2021   AIC                         -17215.608
Time:                        17:11:20   BIC                         -17065.501
Sample:                             0   HQIC                        -17157.961
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -4.057e-09   5.82e-05  -6.97e-05      1.000      -0.000       0.000
x2         -4.057e-09   5.81e-05  -6.99e-05      1.000      -0.000       0.000
x3         -4.111e-09   5.49e-05  -7.49e-05      1.000      -0.000       0.000
x4             1.0000   5.71e-05   1.75e+04      0.000       1.000       1.000
x5         -3.706e-09   5.43e-05  -6.82e-05      1.000      -0.000       0.000
x6         -1.082e-08      0.000  -6.08e-05      1.000      -0.000       0.000
x7         -4.025e-09   5.63e-05  -7.15e-05      1.000      -0.000       0.000
x8         -4.035e-09   5.19e-05  -7.78e-05      1.000      -0.000       0.000
x9         -1.522e-10    2.9e-05  -5.25e-06      1.000   -5.68e-05    5.68e-05
x10        -6.396e-10   1.04e-05  -6.15e-05      1.000   -2.04e-05    2.04e-05
x11        -3.921e-09   5.06e-05  -7.75e-05      1.000   -9.91e-05    9.91e-05
x12        -4.102e-09   5.29e-05  -7.76e-05      1.000      -0.000       0.000
x13        -4.087e-09   5.75e-05  -7.11e-05      1.000      -0.000       0.000
x14        -3.619e-08      0.000     -0.000      1.000      -0.000       0.000
x15        -4.806e-09   4.61e-05     -0.000      1.000   -9.03e-05    9.03e-05
x16        -3.507e-09      0.000  -2.98e-05      1.000      -0.000       0.000
x17        -3.121e-09   6.02e-05  -5.18e-05      1.000      -0.000       0.000
x18        -1.172e-08      0.000     -0.000      1.000      -0.000       0.000
x19        -5.433e-09   6.06e-05  -8.96e-05      1.000      -0.000       0.000
x20        -1.393e-08   4.79e-05     -0.000      1.000   -9.39e-05    9.39e-05
x21        -4.216e-09   6.63e-05  -6.36e-05      1.000      -0.000       0.000
x22        -3.479e-11   1.66e-08     -0.002      0.998   -3.25e-08    3.24e-08
x23        -9.221e-10    1.4e-07     -0.007      0.995   -2.74e-07    2.73e-07
x24        -8.085e-08      0.001  -6.96e-05      1.000      -0.002       0.002
x25        -9.642e-08      0.001     -0.000      1.000      -0.002       0.002
x26        -5.019e-08      0.000     -0.000      1.000      -0.000       0.000
x27        -2.457e-08   7.65e-05     -0.000      1.000      -0.000       0.000
x28        -3.411e-08      0.000     -0.000      1.000      -0.000       0.000
x29        -1.507e-08   4.36e-05     -0.000      1.000   -8.54e-05    8.54e-05
ma.L1         -1.3898   8.03e-07  -1.73e+06      0.000      -1.390      -1.390
ma.L2          0.4031   8.36e-07   4.82e+05      0.000       0.403       0.403
sigma2      7.528e-11   7.24e-11      1.040      0.298   -6.66e-11    2.17e-10
===================================================================================
Ljung-Box (L1) (Q):                  89.12   Jarque-Bera (JB):           1533103.33
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             5.56
Prob(H) (two-sided):                  0.00   Kurtosis:                       216.50
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.08e+25. Standard errors may be unstable.
ARIMA order: (0, 3, 2)

/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  super(Adam, self).__init__(name, **kwargs)

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04685, saving model to LSTM6.h5
48/48 - 3s - loss: 0.1506 - accuracy: 0.0000e+00 - val_loss: 0.0468 - val_accuracy: 0.0037 - lr: 0.0010 - 3s/epoch - 71ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.04685 to 0.00855, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0267 - accuracy: 0.0000e+00 - val_loss: 0.0085 - val_accuracy: 0.0037 - lr: 0.0010 - 291ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.00855
48/48 - 0s - loss: 0.0284 - accuracy: 0.0000e+00 - val_loss: 0.0544 - val_accuracy: 0.0037 - lr: 0.0010 - 249ms/epoch - 5ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.00855
48/48 - 0s - loss: 0.0260 - accuracy: 0.0000e+00 - val_loss: 0.0121 - val_accuracy: 0.0037 - lr: 0.0010 - 273ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00855
48/48 - 0s - loss: 0.0112 - accuracy: 0.0000e+00 - val_loss: 0.0529 - val_accuracy: 0.0037 - lr: 0.0010 - 283ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00855
48/48 - 0s - loss: 0.0128 - accuracy: 0.0000e+00 - val_loss: 0.0290 - val_accuracy: 0.0037 - lr: 0.0010 - 252ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00007: val_loss did not improve from 0.00855
48/48 - 0s - loss: 0.0119 - accuracy: 0.0000e+00 - val_loss: 0.0662 - val_accuracy: 0.0037 - lr: 0.0010 - 279ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00855
48/48 - 0s - loss: 0.0206 - accuracy: 0.0000e+00 - val_loss: 0.0188 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 303ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.00855
48/48 - 0s - loss: 0.0037 - accuracy: 0.0000e+00 - val_loss: 0.0127 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 267ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.00855 to 0.00839, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0030 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 275ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.00839 to 0.00607, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0026 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 277ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.00607 to 0.00490, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0023 - accuracy: 0.0000e+00 - val_loss: 0.0049 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 290ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.00490 to 0.00436, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0020 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 319ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.00436 to 0.00414, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0018 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 269ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss improved from 0.00414 to 0.00405, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 319ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: val_loss improved from 0.00405 to 0.00401, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0016 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 288ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.00401 to 0.00399, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0015 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 284ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss improved from 0.00399 to 0.00395, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0014 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 298ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss improved from 0.00395 to 0.00392, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 289ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.00392 to 0.00388, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 295ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss improved from 0.00388 to 0.00383, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 283ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss improved from 0.00383 to 0.00379, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 301ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss improved from 0.00379 to 0.00375, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 298ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss improved from 0.00375 to 0.00371, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 322ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss improved from 0.00371 to 0.00368, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 271ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss improved from 0.00368 to 0.00365, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 314ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss improved from 0.00365 to 0.00362, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 293ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss improved from 0.00362 to 0.00360, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 290ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss improved from 0.00360 to 0.00359, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 326ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss improved from 0.00359 to 0.00358, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 269ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00031: val_loss improved from 0.00358 to 0.00358, saving model to LSTM6.h5
48/48 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 304ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.2863e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 284ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.2266e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 281ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.2009e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 244ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.1823e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 266ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00036: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.1660e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 269ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.1507e-04 - accuracy: 0.0000e+00 - val_loss: 0.0036 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 255ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.1360e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 278ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.1219e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 279ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.1081e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 289ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.0946e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 316ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.0813e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 299ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.0682e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 295ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.0553e-04 - accuracy: 0.0000e+00 - val_loss: 0.0037 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 283ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.0426e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 287ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.0299e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 284ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.0173e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 304ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00358
48/48 - 0s - loss: 9.0048e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 294ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.9923e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 275ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.9799e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.9674e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 280ms/epoch - 6ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.9550e-04 - accuracy: 0.0000e+00 - val_loss: 0.0038 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 275ms/epoch - 6ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.9426e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 281ms/epoch - 6ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.9302e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 251ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.9177e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 263ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.9053e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 289ms/epoch - 6ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.8928e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.8802e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 250ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.8677e-04 - accuracy: 0.0000e+00 - val_loss: 0.0039 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 257ms/epoch - 5ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.8551e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 274ms/epoch - 6ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.8424e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 258ms/epoch - 5ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.8297e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 284ms/epoch - 6ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.8169e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 285ms/epoch - 6ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.8040e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 303ms/epoch - 6ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.7911e-04 - accuracy: 0.0000e+00 - val_loss: 0.0040 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 258ms/epoch - 5ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.7781e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 279ms/epoch - 6ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.7650e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 302ms/epoch - 6ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.7518e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 279ms/epoch - 6ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.7385e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 268ms/epoch - 6ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.7252e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 266ms/epoch - 6ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.7117e-04 - accuracy: 0.0000e+00 - val_loss: 0.0041 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 289ms/epoch - 6ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.6981e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 274ms/epoch - 6ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.6844e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.6707e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 289ms/epoch - 6ms/step
Epoch 75/500

Epoch 00075: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.6568e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 292ms/epoch - 6ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.6427e-04 - accuracy: 0.0000e+00 - val_loss: 0.0042 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 269ms/epoch - 6ms/step
Epoch 77/500

Epoch 00077: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.6286e-04 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 294ms/epoch - 6ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.6144e-04 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 285ms/epoch - 6ms/step
Epoch 79/500

Epoch 00079: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.6000e-04 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 311ms/epoch - 6ms/step
Epoch 80/500

Epoch 00080: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.5855e-04 - accuracy: 0.0000e+00 - val_loss: 0.0043 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 244ms/epoch - 5ms/step
Epoch 81/500

Epoch 00081: val_loss did not improve from 0.00358
48/48 - 0s - loss: 8.5709e-04 - accuracy: 0.0000e+00 - val_loss: 0.0044 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 305ms/epoch - 6ms/step
Epoch 00081: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 75.03401716737034 
RMSE:	 8.662217797271685 
MAPE:	 7.077228582293258
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.778, Time=3.45 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.587, Time=5.48 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15952.568, Time=15.38 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.587, Time=8.39 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16628.634, Time=10.82 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-16462.206, Time=25.75 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16848.298, Time=13.21 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17014.023, Time=6.97 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-16988.619, Time=3.98 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17071.454, Time=8.34 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=inf, Time=18.69 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-16987.994, Time=4.30 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-16982.667, Time=4.98 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 129.764 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8569.727
Date:                Sun, 12 Dec 2021   AIC                         -17071.454
Time:                        17:17:37   BIC                         -16911.966
Sample:                             0   HQIC                        -17010.204
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -2.316e-10   6.25e-05  -3.71e-06      1.000      -0.000       0.000
x2         -2.309e-10   6.24e-05   -3.7e-06      1.000      -0.000       0.000
x3         -2.325e-10   6.26e-05  -3.71e-06      1.000      -0.000       0.000
x4             1.0000   6.25e-05    1.6e+04      0.000       1.000       1.000
x5         -2.107e-10   5.96e-05  -3.54e-06      1.000      -0.000       0.000
x6         -7.997e-10      0.000  -7.41e-06      1.000      -0.000       0.000
x7         -2.295e-10   6.22e-05  -3.69e-06      1.000      -0.000       0.000
x8         -2.246e-10   6.15e-05  -3.65e-06      1.000      -0.000       0.000
x9         -1.167e-11   1.25e-05  -9.33e-07      1.000   -2.45e-05    2.45e-05
x10        -4.454e-11   2.66e-05  -1.68e-06      1.000   -5.21e-05    5.21e-05
x11        -2.221e-10   6.11e-05  -3.63e-06      1.000      -0.000       0.000
x12        -2.266e-10   6.18e-05  -3.66e-06      1.000      -0.000       0.000
x13        -2.315e-10   6.25e-05  -3.71e-06      1.000      -0.000       0.000
x14        -1.767e-09      0.000  -1.02e-05      1.000      -0.000       0.000
x15         -2.11e-10   5.93e-05  -3.56e-06      1.000      -0.000       0.000
x16        -5.283e-10   9.45e-05  -5.59e-06      1.000      -0.000       0.000
x17        -2.098e-10   6.01e-05  -3.49e-06      1.000      -0.000       0.000
x18         -3.82e-11   2.41e-05  -1.58e-06      1.000   -4.73e-05    4.73e-05
x19        -2.645e-10   6.61e-05     -4e-06      1.000      -0.000       0.000
x20        -2.417e-10   6.21e-05  -3.89e-06      1.000      -0.000       0.000
x21        -4.824e-10   8.83e-05  -5.46e-06      1.000      -0.000       0.000
x22        -3.758e-13   1.19e-11     -0.032      0.975   -2.36e-11    2.29e-11
x23        -1.089e-11   8.42e-11     -0.129      0.897   -1.76e-10    1.54e-10
x24        -2.538e-09      0.000  -1.44e-05      1.000      -0.000       0.000
x25        -2.038e-09      0.000  -1.49e-05      1.000      -0.000       0.000
x26         -3.16e-09      0.000  -1.37e-05      1.000      -0.000       0.000
x27        -2.955e-09      0.000  -1.32e-05      1.000      -0.000       0.000
x28        -1.664e-09      0.000  -9.94e-06      1.000      -0.000       0.000
x29        -1.568e-09      0.000  -9.63e-06      1.000      -0.000       0.000
ar.L1         -0.4923    6.2e-10  -7.94e+08      0.000      -0.492      -0.492
ar.L2         -0.1923    3.6e-10  -5.35e+08      0.000      -0.192      -0.192
ar.L3         -0.0462   1.71e-10  -2.71e+08      0.000      -0.046      -0.046
ma.L1         -0.7077   1.41e-09  -5.04e+08      0.000      -0.708      -0.708
sigma2       8.99e-11   6.96e-11      1.291      0.197   -4.66e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  51.79   Jarque-Bera (JB):           4012066.18
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.44
Prob(H) (two-sided):                  0.00   Kurtosis:                       348.68
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 5.01e+30. Standard errors may be unstable.
ARIMA order: (3, 3, 1)

/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  super(Adam, self).__init__(name, **kwargs)

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.00799, saving model to LSTM6.h5
16/16 - 3s - loss: 0.0776 - accuracy: 0.0000e+00 - val_loss: 0.0080 - val_accuracy: 0.0037 - lr: 0.0010 - 3s/epoch - 218ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.00799
16/16 - 0s - loss: 0.0318 - accuracy: 0.0000e+00 - val_loss: 0.1262 - val_accuracy: 0.0000e+00 - lr: 0.0010 - 100ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.00799
16/16 - 0s - loss: 0.0517 - accuracy: 0.0000e+00 - val_loss: 0.0132 - val_accuracy: 0.0037 - lr: 0.0010 - 113ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.00799 to 0.00501, saving model to LSTM6.h5
16/16 - 0s - loss: 0.0237 - accuracy: 0.0000e+00 - val_loss: 0.0050 - val_accuracy: 0.0037 - lr: 0.0010 - 135ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0243 - accuracy: 0.0000e+00 - val_loss: 0.0101 - val_accuracy: 0.0037 - lr: 0.0010 - 105ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0106 - accuracy: 0.0000e+00 - val_loss: 0.0249 - val_accuracy: 0.0037 - lr: 0.0010 - 104ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0154 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 0.0010 - 107ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0048 - accuracy: 0.0000e+00 - val_loss: 0.0084 - val_accuracy: 0.0037 - lr: 0.0010 - 119ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00009: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0070 - accuracy: 0.0000e+00 - val_loss: 0.0081 - val_accuracy: 0.0037 - lr: 0.0010 - 110ms/epoch - 7ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0017 - accuracy: 0.0000e+00 - val_loss: 0.0079 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 99ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0073 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 100ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0013 - accuracy: 0.0000e+00 - val_loss: 0.0067 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 120ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0012 - accuracy: 0.0000e+00 - val_loss: 0.0063 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 114ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00014: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-04 - 121ms/epoch - 8ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0061 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00019: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0060 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0011 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 127ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 120ms/epoch - 8ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0059 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 119ms/epoch - 7ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 121ms/epoch - 8ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 122ms/epoch - 8ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 119ms/epoch - 7ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 119ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 117ms/epoch - 7ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.00501
16/16 - 0s - loss: 0.0010 - accuracy: 0.0000e+00 - val_loss: 0.0058 - val_accuracy: 0.0037 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 00054: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.51% Accuracy
MSE:	 75.03401716737034 
RMSE:	 8.662217797271685 
MAPE:	 7.077228582293258

EMA
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	45.15% Accuracy
MSE:	 70.28436187942754 
RMSE:	 8.383576914386099 
MAPE:	 6.876111393338704
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.778, Time=3.57 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.587, Time=5.37 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-14597.576, Time=5.63 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.587, Time=8.21 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15338.693, Time=11.46 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15153.472, Time=27.75 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-17112.658, Time=16.25 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-14552.587, Time=10.68 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-15106.216, Time=14.92 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-12251.715, Time=36.41 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 140.271 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8588.329
Date:                Sun, 12 Dec 2021   AIC                         -17112.658
Time:                        17:28:56   BIC                         -16962.551
Sample:                             0   HQIC                        -17055.011
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1          -4.53e-09   3.26e-06     -0.001      0.999   -6.39e-06    6.38e-06
x2         -4.512e-09   3.25e-06     -0.001      0.999   -6.38e-06    6.37e-06
x3         -4.538e-09   3.26e-06     -0.001      0.999    -6.4e-06    6.39e-06
x4             1.0000   3.26e-06   3.07e+05      0.000       1.000       1.000
x5         -4.105e-09   3.11e-06     -0.001      0.999    -6.1e-06    6.09e-06
x6         -1.488e-08   5.45e-06     -0.003      0.998   -1.07e-05    1.07e-05
x7         -4.481e-09   3.24e-06     -0.001      0.999   -6.36e-06    6.36e-06
x8         -4.365e-09    3.2e-06     -0.001      0.999   -6.29e-06    6.28e-06
x9         -4.628e-10   8.38e-07     -0.001      1.000   -1.64e-06    1.64e-06
x10        -7.326e-10    1.3e-06     -0.001      1.000   -2.55e-06    2.54e-06
x11        -4.347e-09    3.2e-06     -0.001      0.999   -6.27e-06    6.26e-06
x12        -4.345e-09    3.2e-06     -0.001      0.999   -6.27e-06    6.26e-06
x13         -4.52e-09   3.26e-06     -0.001      0.999   -6.39e-06    6.38e-06
x14        -3.586e-08      9e-06     -0.004      0.997   -1.77e-05    1.76e-05
x15        -3.757e-09   2.98e-06     -0.001      0.999   -5.84e-06    5.83e-06
x16         -1.24e-08   5.36e-06     -0.002      0.998   -1.05e-05    1.05e-05
x17        -4.515e-09   3.26e-06     -0.001      0.999    -6.4e-06    6.39e-06
x18        -2.632e-10   7.07e-07     -0.000      1.000   -1.39e-06    1.39e-06
x19        -4.642e-09    3.3e-06     -0.001      0.999   -6.47e-06    6.46e-06
x20        -3.919e-10   6.91e-07     -0.001      1.000   -1.36e-06    1.35e-06
x21         -7.69e-09   4.13e-06     -0.002      0.999   -8.11e-06    8.09e-06
x22        -6.998e-12   2.69e-13    -25.970      0.000   -7.53e-12   -6.47e-12
x23         -1.81e-10   2.22e-12    -81.582      0.000   -1.85e-10   -1.77e-10
x24        -4.955e-08    8.9e-06     -0.006      0.996   -1.75e-05    1.74e-05
x25        -4.901e-08    8.4e-06     -0.006      0.995   -1.65e-05    1.64e-05
x26        -6.446e-08    1.2e-05     -0.005      0.996   -2.37e-05    2.35e-05
x27         -5.73e-08   1.14e-05     -0.005      0.996   -2.24e-05    2.23e-05
x28        -2.997e-08   8.22e-06     -0.004      0.997   -1.61e-05    1.61e-05
x29        -3.486e-08   8.89e-06     -0.004      0.997   -1.75e-05    1.74e-05
ma.L1         -1.3902   3.62e-10  -3.84e+09      0.000      -1.390      -1.390
ma.L2          0.4033   3.72e-10   1.08e+09      0.000       0.403       0.403
sigma2      8.541e-11   6.95e-11      1.229      0.219   -5.08e-11    2.22e-10
===================================================================================
Ljung-Box (L1) (Q):                  66.92   Jarque-Bera (JB):           6039240.46
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                            12.14
Prob(H) (two-sided):                  0.00   Kurtosis:                       426.63
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.94e+30. Standard errors may be unstable.
ARIMA order: (0, 3, 2)

/usr/local/lib/python3.7/dist-packages/keras/optimizer_v2/adam.py:105: UserWarning: The `lr` argument is deprecated, use `learning_rate` instead.
  super(Adam, self).__init__(name, **kwargs)

Architecture Used¶

from google.colab import files
import cv2
uploaded = files.upload()

Saving Experiment6.png to Experiment6 (1).png

img = cv2.imread('Experiment6.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)

<matplotlib.image.AxesImage at 0x7fa5cfcc6b10>

Model Plots¶

for i in range(len(list(simulation6.keys()))):
  SIM = list(simulation6.keys())[i]
  plot_train(simulation6,SIM)
  plot_test(simulation6,SIM)

----- Train RMSE for SMA ----- 8.882238711112084
----- Train_MSE_LSTM for SMA ----- 78.89416452117804
----- Train MAE LSTM for SMA ----- 7.762640273567326

----- Test RMSE for SMA----- 8.662217797271685
----- Test_MSE_LSTM for SMA----- 75.03401716737034
----- Test_MAE_LSTM for SMA----- 7.077228582293258

----- Train RMSE for EMA ----- 10.160180455912146
----- Train_MSE_LSTM for EMA ----- 103.22926689669913
----- Train MAE LSTM for EMA ----- 9.005262034617845

----- Test RMSE for EMA----- 8.383576914386099
----- Test_MSE_LSTM for EMA----- 70.28436187942754
----- Test_MAE_LSTM for EMA----- 6.876111393338704

----- Train RMSE for WMA ----- 10.433402093205265
----- Train_MSE_LSTM for WMA ----- 108.85587923850001
----- Train MAE LSTM for WMA ----- 9.27337175169683

----- Test RMSE for WMA----- 8.400646538592587
----- Test_MSE_LSTM for WMA----- 70.57086226636761
----- Test_MAE_LSTM for WMA----- 6.6664001460728475

----- Train RMSE for DEMA ----- 12.041548116714113
----- Train_MSE_LSTM for DEMA ----- 144.9988810471412
----- Train MAE LSTM for DEMA ----- 10.79869721264182

----- Test RMSE for DEMA----- 18.15498746735199
----- Test_MSE_LSTM for DEMA----- 329.6035699397079
----- Test_MAE_LSTM for DEMA----- 16.799244301034683

----- Train RMSE for KAMA ----- 10.551998588436238
----- Train_MSE_LSTM for KAMA ----- 111.34467421036034
----- Train MAE LSTM for KAMA ----- 9.496739060524044

----- Test RMSE for KAMA----- 10.162400289890599
----- Test_MSE_LSTM for KAMA----- 103.27437965196852
----- Test_MAE_LSTM for KAMA----- 8.510636158449836

Arima w Exogenous Variable Multistep MutiVariate LSTM Hybrid Model Experiment 7¶

def get_arima_exog(dataframe,original_data, train_len, test_len):    
    

    # prepare train and test data for exogenous vr
    X_value = pd.DataFrame(low_vol.iloc[:, :])
    y_value = pd.DataFrame(low_vol.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    X_scale_dataset = X_scaler.fit_transform(X_value)
    y_scale_dataset = y_scaler.fit_transform(y_value)
    # Get data and check shape
    # X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X_scale_dataset)
    y_train, y_test, = split_train_test(y_scale_dataset)
    yc_train,yc_test = split_train_test(low_vol_data)
    yc = yc_test.values.tolist()
    y_train_list = y_train.flatten().tolist()
    y_test_list = y_test.flatten().tolist()
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)

    # Initialize model
    model = auto_arima(y_train_list,exogenous  = X_train,trace=True, error_action='ignore', start_p=1,start_q=1,max_p=3,max_q=3,d=3,
            suppress_warnings=True,stepwise=True,seasonal=True)

      # Determine model parameters
    print(model.summary())
    model.fit(y_train_list,maxiter=200)
    order = model.get_params()['order']
    print('ARIMA order:', order, '\n')

      # Genereate predictions
    prediction = []
    for i in range(len(y_test_list)):
        model = pmdarima.ARIMA(order=order)
        model.fit(y_train_list)
        # print('working on', i+1, 'of', len(y_test), '-- ' + str(int(100 * (i + 1) / len(y_test))) + '% complete')

        prediction.append(model.predict()[0])
        y_train_list.append(y_test_list[i])

    predictionte = y_scaler.inverse_transform(np.array(prediction).reshape(-1,1))
    y_test_ = y_scaler.inverse_transform(np.array(y_test_list).reshape(-1,1))

    # Generate error data
    mse = mean_squared_error(yc_test, predictionte)
    rmse = mse ** 0.5
    mae = mean_absolute_error(y_test_ , predictionte )
    return yc,predictionte.flatten().tolist(), mse, rmse, mae

def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det =20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # Option 1
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    # model.add(Dense(units=64,activation='relu'))
    # model.add(Dropout(0.5))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    # ## Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()


    # # # option 2
    # model = Sequential()
    # model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    # model.add(Dense(64))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM7.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma+' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 3
    # define custom activation
    # reference: https://github.com/Vaibhav-Sachdeva/Correlation-Coefficient-Prediction-using-ARIMA-LSTM-Hybrid-Model/blob/main/Code/LSTM-ARIMA.ipynb
    class Double_Tanh(Activation):
        def __init__(self, activation, **kwargs):
            super(Double_Tanh, self).__init__(activation, **kwargs)
            self.__name__ = 'double_tanh'

    def double_tanh(x):
        return (K.tanh(x) * 2)

    get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
        # Model Generation
    model = Sequential()
    #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    model.add(Dense(1))
    model.add(Activation(double_tanh))
    model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM7.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()

    # Option 4
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(x_train.shape[1], 1)))
    # model.add(LSTM(units=int(lstm_len/2)))
    # model.add(Dense(1, activation='sigmoid'))
    # model.compile(loss='mean_squared_error', optimizer='adam')
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te

if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation7 = {}
    imgfile = 'Experiment7'
    for ma in optimized_period:
                print(ma)
                print(functions[ma])
                print ( int( optimized_period[ma]))
              # if ma == 'SMA':
                low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
                low_vol = low_vol.fillna(0)
                low_vol_data = df['close']
                high_vol = pd.DataFrame()
                df2 = df.copy()
                for i in df2.columns:
                  if i in low_vol.columns:
                    high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
                high_vol_data = df['close']
                ## *****************************************************
                # Generate ARIMA and LSTM predictions
                print('\nWorking on ' + ma + ' predictions')
                try:
                  print('parameters used : ', train_len, test_len)
                  low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima_exog(low_vol,low_vol_data, train_len, test_len)
                except:
                    print('ARIMA error, skipping to next MA type')
                    continue
                Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
                final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
                mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
                rmse_ftr = mse_ftr ** 0.5
                mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
                mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

                final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
                mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
                rmse = mse ** 0.5
                mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                # Generate prediction accuracy
                actual = df['close'].tail(test_len).values
                result_1 = []
                result_2 = []
                for i in range(1, len(final_prediction)):
                    # Compare prediction to previous close price
                    if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                        result_1.append(1)
                    elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                        result_1.append(1)
                    else:
                        result_1.append(0)

                    # Compare prediction to previous prediction
                    if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                        result_2.append(1)
                    elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                        result_2.append(1)
                    else:
                        result_2.append(0)

                accuracy_1 = np.mean(result_1)
                accuracy_2 = np.mean(result_2)

                simulation7[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                              'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                  'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                              'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                  'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                              'rmse': rmse_ftr, 'mae' : mae_ftr},
                                  'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                            'rmse': rmse, 'mae': mae },
                                  'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

                # save simulation data here as checkpoint
                with open('simulation7_data.json', 'w') as fp:
                    json.dump(simulation7, fp)

                for ma in simulation7.keys():
                    print('\n' + ma)
                    print('Prediction vs Close:\t\t' + str(round(100*simulation7[ma]['accuracy']['prediction vs close'], 2))
                          + '% Accuracy')
                    print('Prediction vs Prediction:\t' + str(round(100*simulation7[ma]['accuracy']['prediction vs prediction'], 2))
                          + '% Accuracy')
                    print('MSE:\t', simulation7[ma]['final']['mse'],
                          '\nRMSE:\t', simulation7[ma]['final']['rmse'],
                          '\nMAPE:\t', simulation7[ma]['final']['mae'])#,
                          # '\nMAPE:\t', simulation[ma]['final']['mape'])
              # else:
              #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.787, Time=3.58 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.588, Time=5.63 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-14596.280, Time=5.74 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.588, Time=8.45 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16924.805, Time=10.66 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-14482.349, Time=11.42 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-17215.608, Time=20.46 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-14552.588, Time=11.13 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-15570.350, Time=19.72 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-11671.292, Time=28.32 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 125.145 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8639.804
Date:                Sun, 12 Dec 2021   AIC                         -17215.608
Time:                        18:11:46   BIC                         -17065.501
Sample:                             0   HQIC                        -17157.961
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -4.057e-09   5.82e-05  -6.97e-05      1.000      -0.000       0.000
x2         -4.057e-09   5.81e-05  -6.99e-05      1.000      -0.000       0.000
x3         -4.111e-09   5.49e-05  -7.49e-05      1.000      -0.000       0.000
x4             1.0000   5.71e-05   1.75e+04      0.000       1.000       1.000
x5         -3.706e-09   5.43e-05  -6.82e-05      1.000      -0.000       0.000
x6         -1.082e-08      0.000  -6.08e-05      1.000      -0.000       0.000
x7         -4.025e-09   5.63e-05  -7.15e-05      1.000      -0.000       0.000
x8         -4.035e-09   5.19e-05  -7.78e-05      1.000      -0.000       0.000
x9         -1.522e-10    2.9e-05  -5.25e-06      1.000   -5.68e-05    5.68e-05
x10        -6.396e-10   1.04e-05  -6.15e-05      1.000   -2.04e-05    2.04e-05
x11        -3.921e-09   5.06e-05  -7.75e-05      1.000   -9.91e-05    9.91e-05
x12        -4.102e-09   5.29e-05  -7.76e-05      1.000      -0.000       0.000
x13        -4.087e-09   5.75e-05  -7.11e-05      1.000      -0.000       0.000
x14        -3.619e-08      0.000     -0.000      1.000      -0.000       0.000
x15        -4.806e-09   4.61e-05     -0.000      1.000   -9.03e-05    9.03e-05
x16        -3.507e-09      0.000  -2.98e-05      1.000      -0.000       0.000
x17        -3.121e-09   6.02e-05  -5.18e-05      1.000      -0.000       0.000
x18        -1.172e-08      0.000     -0.000      1.000      -0.000       0.000
x19        -5.433e-09   6.06e-05  -8.96e-05      1.000      -0.000       0.000
x20        -1.393e-08   4.79e-05     -0.000      1.000   -9.39e-05    9.39e-05
x21        -4.216e-09   6.63e-05  -6.36e-05      1.000      -0.000       0.000
x22        -3.479e-11   1.66e-08     -0.002      0.998   -3.25e-08    3.24e-08
x23        -9.221e-10    1.4e-07     -0.007      0.995   -2.74e-07    2.73e-07
x24        -8.085e-08      0.001  -6.96e-05      1.000      -0.002       0.002
x25        -9.642e-08      0.001     -0.000      1.000      -0.002       0.002
x26        -5.019e-08      0.000     -0.000      1.000      -0.000       0.000
x27        -2.457e-08   7.65e-05     -0.000      1.000      -0.000       0.000
x28        -3.411e-08      0.000     -0.000      1.000      -0.000       0.000
x29        -1.507e-08   4.36e-05     -0.000      1.000   -8.54e-05    8.54e-05
ma.L1         -1.3898   8.03e-07  -1.73e+06      0.000      -1.390      -1.390
ma.L2          0.4031   8.36e-07   4.82e+05      0.000       0.403       0.403
sigma2      7.528e-11   7.24e-11      1.040      0.298   -6.66e-11    2.17e-10
===================================================================================
Ljung-Box (L1) (Q):                  89.12   Jarque-Bera (JB):           1533103.33
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             5.56
Prob(H) (two-sided):                  0.00   Kurtosis:                       216.50
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.08e+25. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.32789, saving model to LSTM7.h5
48/48 - 2s - loss: 0.0877 - mse: 0.0877 - mae: 0.2289 - val_loss: 0.3279 - val_mse: 0.3279 - val_mae: 0.5464 - lr: 0.0010 - 2s/epoch - 44ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.32789 to 0.08109, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0258 - mse: 0.0258 - mae: 0.1276 - val_loss: 0.0811 - val_mse: 0.0811 - val_mae: 0.2555 - lr: 0.0010 - 243ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.08109
48/48 - 0s - loss: 0.0165 - mse: 0.0165 - mae: 0.1010 - val_loss: 0.0825 - val_mse: 0.0825 - val_mae: 0.2611 - lr: 0.0010 - 200ms/epoch - 4ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.08109 to 0.06805, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0124 - mse: 0.0124 - mae: 0.0885 - val_loss: 0.0680 - val_mse: 0.0680 - val_mae: 0.2354 - lr: 0.0010 - 238ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.06805
48/48 - 0s - loss: 0.0099 - mse: 0.0099 - mae: 0.0771 - val_loss: 0.0897 - val_mse: 0.0897 - val_mae: 0.2766 - lr: 0.0010 - 208ms/epoch - 4ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.06805 to 0.04796, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0111 - mse: 0.0111 - mae: 0.0810 - val_loss: 0.0480 - val_mse: 0.0480 - val_mae: 0.1935 - lr: 0.0010 - 232ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04796
48/48 - 0s - loss: 0.0080 - mse: 0.0080 - mae: 0.0693 - val_loss: 0.0706 - val_mse: 0.0706 - val_mae: 0.2443 - lr: 0.0010 - 252ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.04796 to 0.03656, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0701 - val_loss: 0.0366 - val_mse: 0.0366 - val_mae: 0.1669 - lr: 0.0010 - 286ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.03656
48/48 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0662 - val_loss: 0.0638 - val_mse: 0.0638 - val_mae: 0.2318 - lr: 0.0010 - 261ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.03656
48/48 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0694 - val_loss: 0.0548 - val_mse: 0.0548 - val_mae: 0.2136 - lr: 0.0010 - 265ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.03656
48/48 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0650 - val_loss: 0.0632 - val_mse: 0.0632 - val_mae: 0.2304 - lr: 0.0010 - 240ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.03656
48/48 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0685 - val_loss: 0.0450 - val_mse: 0.0450 - val_mae: 0.1907 - lr: 0.0010 - 227ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00013: val_loss did not improve from 0.03656
48/48 - 0s - loss: 0.0092 - mse: 0.0092 - mae: 0.0769 - val_loss: 0.0858 - val_mse: 0.0858 - val_mae: 0.2735 - lr: 0.0010 - 210ms/epoch - 4ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.03656
48/48 - 0s - loss: 0.0259 - mse: 0.0259 - mae: 0.1392 - val_loss: 0.0416 - val_mse: 0.0416 - val_mae: 0.1834 - lr: 1.0000e-04 - 237ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.03656
48/48 - 0s - loss: 0.0117 - mse: 0.0117 - mae: 0.0881 - val_loss: 0.0401 - val_mse: 0.0401 - val_mae: 0.1790 - lr: 1.0000e-04 - 244ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.03656
48/48 - 0s - loss: 0.0103 - mse: 0.0103 - mae: 0.0820 - val_loss: 0.0374 - val_mse: 0.0374 - val_mae: 0.1717 - lr: 1.0000e-04 - 212ms/epoch - 4ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.03656 to 0.03439, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0733 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1635 - lr: 1.0000e-04 - 210ms/epoch - 4ms/step
Epoch 18/500

Epoch 00018: val_loss improved from 0.03439 to 0.03341, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0080 - mse: 0.0080 - mae: 0.0722 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1607 - lr: 1.0000e-04 - 251ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss improved from 0.03341 to 0.02962, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0663 - val_loss: 0.0296 - val_mse: 0.0296 - val_mae: 0.1495 - lr: 1.0000e-04 - 243ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss improved from 0.02962 to 0.02867, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0706 - val_loss: 0.0287 - val_mse: 0.0287 - val_mae: 0.1466 - lr: 1.0000e-04 - 271ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss improved from 0.02867 to 0.02677, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0657 - val_loss: 0.0268 - val_mse: 0.0268 - val_mae: 0.1406 - lr: 1.0000e-04 - 252ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.02677
48/48 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0631 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1410 - lr: 1.0000e-04 - 271ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.02677
48/48 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0636 - val_loss: 0.0272 - val_mse: 0.0272 - val_mae: 0.1423 - lr: 1.0000e-04 - 232ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss improved from 0.02677 to 0.02567, saving model to LSTM7.h5
48/48 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0582 - val_loss: 0.0257 - val_mse: 0.0257 - val_mae: 0.1371 - lr: 1.0000e-04 - 242ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0643 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1380 - lr: 1.0000e-04 - 198ms/epoch - 4ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0625 - val_loss: 0.0275 - val_mse: 0.0275 - val_mae: 0.1432 - lr: 1.0000e-04 - 200ms/epoch - 4ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0583 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1469 - lr: 1.0000e-04 - 226ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0598 - val_loss: 0.0295 - val_mse: 0.0295 - val_mae: 0.1493 - lr: 1.0000e-04 - 207ms/epoch - 4ms/step
Epoch 29/500

Epoch 00029: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00029: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0618 - val_loss: 0.0302 - val_mse: 0.0302 - val_mae: 0.1514 - lr: 1.0000e-04 - 199ms/epoch - 4ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0567 - val_loss: 0.0305 - val_mse: 0.0305 - val_mae: 0.1522 - lr: 1.0000e-05 - 191ms/epoch - 4ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0551 - val_loss: 0.0308 - val_mse: 0.0308 - val_mae: 0.1532 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0545 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1545 - lr: 1.0000e-05 - 213ms/epoch - 4ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0557 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1551 - lr: 1.0000e-05 - 264ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00034: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0542 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1556 - lr: 1.0000e-05 - 215ms/epoch - 4ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0555 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1561 - lr: 1.0000e-05 - 199ms/epoch - 4ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0564 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1567 - lr: 1.0000e-05 - 243ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0556 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1573 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0544 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1575 - lr: 1.0000e-05 - 207ms/epoch - 4ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0539 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1571 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0543 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1567 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0555 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1568 - lr: 1.0000e-05 - 241ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0534 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1576 - lr: 1.0000e-05 - 205ms/epoch - 4ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0570 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1578 - lr: 1.0000e-05 - 207ms/epoch - 4ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0513 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1589 - lr: 1.0000e-05 - 225ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0547 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1591 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0552 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1594 - lr: 1.0000e-05 - 201ms/epoch - 4ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0523 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1594 - lr: 1.0000e-05 - 219ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0523 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1598 - lr: 1.0000e-05 - 228ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0525 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1589 - lr: 1.0000e-05 - 255ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0533 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1594 - lr: 1.0000e-05 - 255ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0531 - val_loss: 0.0330 - val_mse: 0.0330 - val_mae: 0.1596 - lr: 1.0000e-05 - 229ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0552 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1591 - lr: 1.0000e-05 - 226ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0520 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1590 - lr: 1.0000e-05 - 229ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0537 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1583 - lr: 1.0000e-05 - 241ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0042 - mse: 0.0042 - mae: 0.0517 - val_loss: 0.0325 - val_mse: 0.0325 - val_mae: 0.1583 - lr: 1.0000e-05 - 217ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0542 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1589 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0515 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1591 - lr: 1.0000e-05 - 190ms/epoch - 4ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0536 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1589 - lr: 1.0000e-05 - 240ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0546 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1592 - lr: 1.0000e-05 - 240ms/epoch - 5ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0551 - val_loss: 0.0325 - val_mse: 0.0325 - val_mae: 0.1581 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0540 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1583 - lr: 1.0000e-05 - 242ms/epoch - 5ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0557 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1585 - lr: 1.0000e-05 - 221ms/epoch - 5ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0515 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1593 - lr: 1.0000e-05 - 236ms/epoch - 5ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0540 - val_loss: 0.0328 - val_mse: 0.0328 - val_mae: 0.1590 - lr: 1.0000e-05 - 241ms/epoch - 5ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0551 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1580 - lr: 1.0000e-05 - 230ms/epoch - 5ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0520 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1578 - lr: 1.0000e-05 - 232ms/epoch - 5ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0529 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1599 - lr: 1.0000e-05 - 266ms/epoch - 6ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0551 - val_loss: 0.0332 - val_mse: 0.0332 - val_mae: 0.1602 - lr: 1.0000e-05 - 202ms/epoch - 4ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0550 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1597 - lr: 1.0000e-05 - 234ms/epoch - 5ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0525 - val_loss: 0.0330 - val_mse: 0.0330 - val_mae: 0.1595 - lr: 1.0000e-05 - 243ms/epoch - 5ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0509 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1604 - lr: 1.0000e-05 - 219ms/epoch - 5ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0517 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1603 - lr: 1.0000e-05 - 245ms/epoch - 5ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0534 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1610 - lr: 1.0000e-05 - 203ms/epoch - 4ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.02567
48/48 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0553 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1607 - lr: 1.0000e-05 - 209ms/epoch - 4ms/step
Epoch 00074: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 44.65212926265077 
RMSE:	 6.682224873696692 
MAPE:	 5.204686480071648
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.778, Time=3.80 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.587, Time=5.48 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15952.568, Time=15.31 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.587, Time=8.47 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16628.634, Time=10.28 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-16462.206, Time=25.09 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16848.298, Time=13.32 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17014.023, Time=6.57 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-16988.619, Time=3.49 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17071.454, Time=7.51 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=inf, Time=18.51 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-16987.994, Time=4.01 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-16982.667, Time=4.43 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 126.280 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8569.727
Date:                Sun, 12 Dec 2021   AIC                         -17071.454
Time:                        18:17:53   BIC                         -16911.966
Sample:                             0   HQIC                        -17010.204
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -2.316e-10   6.25e-05  -3.71e-06      1.000      -0.000       0.000
x2         -2.309e-10   6.24e-05   -3.7e-06      1.000      -0.000       0.000
x3         -2.325e-10   6.26e-05  -3.71e-06      1.000      -0.000       0.000
x4             1.0000   6.25e-05    1.6e+04      0.000       1.000       1.000
x5         -2.107e-10   5.96e-05  -3.54e-06      1.000      -0.000       0.000
x6         -7.997e-10      0.000  -7.41e-06      1.000      -0.000       0.000
x7         -2.295e-10   6.22e-05  -3.69e-06      1.000      -0.000       0.000
x8         -2.246e-10   6.15e-05  -3.65e-06      1.000      -0.000       0.000
x9         -1.167e-11   1.25e-05  -9.33e-07      1.000   -2.45e-05    2.45e-05
x10        -4.454e-11   2.66e-05  -1.68e-06      1.000   -5.21e-05    5.21e-05
x11        -2.221e-10   6.11e-05  -3.63e-06      1.000      -0.000       0.000
x12        -2.266e-10   6.18e-05  -3.66e-06      1.000      -0.000       0.000
x13        -2.315e-10   6.25e-05  -3.71e-06      1.000      -0.000       0.000
x14        -1.767e-09      0.000  -1.02e-05      1.000      -0.000       0.000
x15         -2.11e-10   5.93e-05  -3.56e-06      1.000      -0.000       0.000
x16        -5.283e-10   9.45e-05  -5.59e-06      1.000      -0.000       0.000
x17        -2.098e-10   6.01e-05  -3.49e-06      1.000      -0.000       0.000
x18         -3.82e-11   2.41e-05  -1.58e-06      1.000   -4.73e-05    4.73e-05
x19        -2.645e-10   6.61e-05     -4e-06      1.000      -0.000       0.000
x20        -2.417e-10   6.21e-05  -3.89e-06      1.000      -0.000       0.000
x21        -4.824e-10   8.83e-05  -5.46e-06      1.000      -0.000       0.000
x22        -3.758e-13   1.19e-11     -0.032      0.975   -2.36e-11    2.29e-11
x23        -1.089e-11   8.42e-11     -0.129      0.897   -1.76e-10    1.54e-10
x24        -2.538e-09      0.000  -1.44e-05      1.000      -0.000       0.000
x25        -2.038e-09      0.000  -1.49e-05      1.000      -0.000       0.000
x26         -3.16e-09      0.000  -1.37e-05      1.000      -0.000       0.000
x27        -2.955e-09      0.000  -1.32e-05      1.000      -0.000       0.000
x28        -1.664e-09      0.000  -9.94e-06      1.000      -0.000       0.000
x29        -1.568e-09      0.000  -9.63e-06      1.000      -0.000       0.000
ar.L1         -0.4923    6.2e-10  -7.94e+08      0.000      -0.492      -0.492
ar.L2         -0.1923    3.6e-10  -5.35e+08      0.000      -0.192      -0.192
ar.L3         -0.0462   1.71e-10  -2.71e+08      0.000      -0.046      -0.046
ma.L1         -0.7077   1.41e-09  -5.04e+08      0.000      -0.708      -0.708
sigma2       8.99e-11   6.96e-11      1.291      0.197   -4.66e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  51.79   Jarque-Bera (JB):           4012066.18
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.44
Prob(H) (two-sided):                  0.00   Kurtosis:                       348.68
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 5.01e+30. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.07245, saving model to LSTM7.h5
16/16 - 2s - loss: 0.6031 - mse: 0.6031 - mae: 0.5816 - val_loss: 0.0725 - val_mse: 0.0725 - val_mae: 0.2175 - lr: 0.0010 - 2s/epoch - 131ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.07245 to 0.05426, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0982 - mse: 0.0982 - mae: 0.2715 - val_loss: 0.0543 - val_mse: 0.0543 - val_mae: 0.1852 - lr: 0.0010 - 96ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.05426 to 0.05329, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0308 - mse: 0.0308 - mae: 0.1410 - val_loss: 0.0533 - val_mse: 0.0533 - val_mae: 0.1773 - lr: 0.0010 - 95ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.05329 to 0.05020, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0288 - mse: 0.0288 - mae: 0.1320 - val_loss: 0.0502 - val_mse: 0.0502 - val_mae: 0.1733 - lr: 0.0010 - 86ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.05020
16/16 - 0s - loss: 0.0203 - mse: 0.0203 - mae: 0.1148 - val_loss: 0.0509 - val_mse: 0.0509 - val_mae: 0.1750 - lr: 0.0010 - 81ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.05020 to 0.04909, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0208 - mse: 0.0208 - mae: 0.1149 - val_loss: 0.0491 - val_mse: 0.0491 - val_mae: 0.1715 - lr: 0.0010 - 89ms/epoch - 6ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.04909 to 0.04433, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0177 - mse: 0.0177 - mae: 0.1061 - val_loss: 0.0443 - val_mse: 0.0443 - val_mae: 0.1622 - lr: 0.0010 - 88ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.04433 to 0.04346, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0156 - mse: 0.0156 - mae: 0.0996 - val_loss: 0.0435 - val_mse: 0.0435 - val_mae: 0.1608 - lr: 0.0010 - 115ms/epoch - 7ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.04346 to 0.04201, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0146 - mse: 0.0146 - mae: 0.0956 - val_loss: 0.0420 - val_mse: 0.0420 - val_mae: 0.1584 - lr: 0.0010 - 107ms/epoch - 7ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.04201 to 0.04017, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0151 - mse: 0.0151 - mae: 0.0974 - val_loss: 0.0402 - val_mse: 0.0402 - val_mae: 0.1550 - lr: 0.0010 - 115ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.04017
16/16 - 0s - loss: 0.0124 - mse: 0.0124 - mae: 0.0884 - val_loss: 0.0406 - val_mse: 0.0406 - val_mae: 0.1565 - lr: 0.0010 - 97ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.04017 to 0.03925, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0125 - mse: 0.0125 - mae: 0.0892 - val_loss: 0.0393 - val_mse: 0.0393 - val_mae: 0.1539 - lr: 0.0010 - 95ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.03925 to 0.03614, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0116 - mse: 0.0116 - mae: 0.0868 - val_loss: 0.0361 - val_mse: 0.0361 - val_mae: 0.1468 - lr: 0.0010 - 99ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.03614 to 0.03480, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0120 - mse: 0.0120 - mae: 0.0858 - val_loss: 0.0348 - val_mse: 0.0348 - val_mae: 0.1438 - lr: 0.0010 - 89ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss improved from 0.03480 to 0.03399, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0094 - mse: 0.0094 - mae: 0.0779 - val_loss: 0.0340 - val_mse: 0.0340 - val_mae: 0.1421 - lr: 0.0010 - 108ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0109 - mse: 0.0109 - mae: 0.0816 - val_loss: 0.0355 - val_mse: 0.0355 - val_mae: 0.1467 - lr: 0.0010 - 74ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0100 - mse: 0.0100 - mae: 0.0800 - val_loss: 0.0348 - val_mse: 0.0348 - val_mae: 0.1455 - lr: 0.0010 - 78ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0093 - mse: 0.0093 - mae: 0.0776 - val_loss: 0.0355 - val_mse: 0.0355 - val_mae: 0.1480 - lr: 0.0010 - 88ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0094 - mse: 0.0094 - mae: 0.0751 - val_loss: 0.0364 - val_mse: 0.0364 - val_mae: 0.1509 - lr: 0.0010 - 85ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00020: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0084 - mse: 0.0084 - mae: 0.0730 - val_loss: 0.0350 - val_mse: 0.0350 - val_mae: 0.1479 - lr: 0.0010 - 96ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0715 - val_loss: 0.0347 - val_mse: 0.0347 - val_mae: 0.1473 - lr: 1.0000e-04 - 95ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0712 - val_loss: 0.0350 - val_mse: 0.0350 - val_mae: 0.1481 - lr: 1.0000e-04 - 83ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0705 - val_loss: 0.0350 - val_mse: 0.0350 - val_mae: 0.1481 - lr: 1.0000e-04 - 77ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0673 - val_loss: 0.0348 - val_mse: 0.0348 - val_mae: 0.1477 - lr: 1.0000e-04 - 76ms/epoch - 5ms/step
Epoch 25/500

Epoch 00025: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00025: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0728 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1467 - lr: 1.0000e-04 - 80ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0733 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1467 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0679 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1467 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0086 - mse: 0.0086 - mae: 0.0743 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1466 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0715 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1466 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00030: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0717 - val_loss: 0.0344 - val_mse: 0.0344 - val_mae: 0.1466 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0711 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1465 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0088 - mse: 0.0088 - mae: 0.0734 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1465 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0091 - mse: 0.0091 - mae: 0.0733 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1465 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0080 - mse: 0.0080 - mae: 0.0703 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1466 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0695 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1466 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0692 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1465 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0713 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1465 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0693 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1464 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0717 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1464 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0697 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1464 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0725 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1463 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0688 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1464 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0689 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1464 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0708 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1464 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0690 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1465 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0726 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1464 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0090 - mse: 0.0090 - mae: 0.0748 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1463 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0669 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1464 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0684 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1463 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0692 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1463 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0730 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1463 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0683 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1463 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0689 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1461 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0684 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1461 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0714 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1462 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0692 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1463 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0702 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1465 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0700 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1465 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0080 - mse: 0.0080 - mae: 0.0712 - val_loss: 0.0343 - val_mse: 0.0343 - val_mae: 0.1466 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0686 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1465 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0086 - mse: 0.0086 - mae: 0.0717 - val_loss: 0.0342 - val_mse: 0.0342 - val_mae: 0.1464 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0704 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1463 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0654 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1462 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.03399
16/16 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0709 - val_loss: 0.0341 - val_mse: 0.0341 - val_mae: 0.1461 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 65/500

Epoch 00065: val_loss improved from 0.03399 to 0.03398, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0715 - val_loss: 0.0340 - val_mse: 0.0340 - val_mae: 0.1458 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 66/500

Epoch 00066: val_loss improved from 0.03398 to 0.03393, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0707 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1457 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.03393
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0694 - val_loss: 0.0340 - val_mse: 0.0340 - val_mae: 0.1458 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.03393
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0687 - val_loss: 0.0340 - val_mse: 0.0340 - val_mae: 0.1459 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.03393
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0666 - val_loss: 0.0340 - val_mse: 0.0340 - val_mae: 0.1459 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.03393
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0689 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1458 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.03393
16/16 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0702 - val_loss: 0.0340 - val_mse: 0.0340 - val_mae: 0.1458 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 72/500

Epoch 00072: val_loss improved from 0.03393 to 0.03390, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0080 - mse: 0.0080 - mae: 0.0700 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1457 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 73/500

Epoch 00073: val_loss improved from 0.03390 to 0.03384, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0689 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1455 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.03384
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0690 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1456 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 75/500

Epoch 00075: val_loss did not improve from 0.03384
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0687 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1457 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.03384
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0704 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1456 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 77/500

Epoch 00077: val_loss improved from 0.03384 to 0.03380, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0693 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1455 - lr: 1.0000e-05 - 117ms/epoch - 7ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.03380
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0667 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1456 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 79/500

Epoch 00079: val_loss did not improve from 0.03380
16/16 - 0s - loss: 0.0088 - mse: 0.0088 - mae: 0.0735 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1456 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 80/500

Epoch 00080: val_loss did not improve from 0.03380
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0676 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1456 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 81/500

Epoch 00081: val_loss did not improve from 0.03380
16/16 - 0s - loss: 0.0082 - mse: 0.0082 - mae: 0.0726 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1457 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 82/500

Epoch 00082: val_loss did not improve from 0.03380
16/16 - 0s - loss: 0.0085 - mse: 0.0085 - mae: 0.0714 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1457 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 83/500

Epoch 00083: val_loss did not improve from 0.03380
16/16 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0693 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1459 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 84/500

Epoch 00084: val_loss did not improve from 0.03380
16/16 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0706 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1458 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 85/500

Epoch 00085: val_loss did not improve from 0.03380
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0678 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1458 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 86/500

Epoch 00086: val_loss did not improve from 0.03380
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0691 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1457 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 87/500

Epoch 00087: val_loss improved from 0.03380 to 0.03380, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0698 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1456 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 88/500

Epoch 00088: val_loss improved from 0.03380 to 0.03380, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0693 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1456 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 89/500

Epoch 00089: val_loss improved from 0.03380 to 0.03375, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0686 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1455 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 90/500

Epoch 00090: val_loss improved from 0.03375 to 0.03368, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0677 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1453 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 91/500

Epoch 00091: val_loss improved from 0.03368 to 0.03367, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0719 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1453 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 92/500

Epoch 00092: val_loss improved from 0.03367 to 0.03367, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0683 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1453 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 93/500

Epoch 00093: val_loss did not improve from 0.03367
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0666 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1455 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 94/500

Epoch 00094: val_loss did not improve from 0.03367
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0695 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1454 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 95/500

Epoch 00095: val_loss improved from 0.03367 to 0.03358, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0703 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1451 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 96/500

Epoch 00096: val_loss improved from 0.03358 to 0.03357, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0645 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1451 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 97/500

Epoch 00097: val_loss improved from 0.03357 to 0.03356, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0670 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1451 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 98/500

Epoch 00098: val_loss did not improve from 0.03356
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0661 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1451 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 99/500

Epoch 00099: val_loss improved from 0.03356 to 0.03352, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0677 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1450 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 100/500

Epoch 00100: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0665 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1453 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 101/500

Epoch 00101: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0679 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1454 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 102/500

Epoch 00102: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0686 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1456 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 103/500

Epoch 00103: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0687 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1456 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 104/500

Epoch 00104: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0703 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1457 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 105/500

Epoch 00105: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0686 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1457 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 106/500

Epoch 00106: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0687 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1456 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 107/500

Epoch 00107: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0679 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1455 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 108/500

Epoch 00108: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0664 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1455 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 109/500

Epoch 00109: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0697 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1457 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 110/500

Epoch 00110: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0701 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1461 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 111/500

Epoch 00111: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0683 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1462 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 112/500

Epoch 00112: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0716 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1462 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 113/500

Epoch 00113: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0667 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1462 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 114/500

Epoch 00114: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0695 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1459 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 115/500

Epoch 00115: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0660 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1460 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 116/500

Epoch 00116: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0706 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1460 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 117/500

Epoch 00117: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0684 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1462 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 118/500

Epoch 00118: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0652 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1463 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 119/500

Epoch 00119: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0079 - mse: 0.0079 - mae: 0.0680 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1463 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 120/500

Epoch 00120: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0681 - val_loss: 0.0338 - val_mse: 0.0338 - val_mae: 0.1462 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 121/500

Epoch 00121: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0683 - val_loss: 0.0339 - val_mse: 0.0339 - val_mae: 0.1463 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 122/500

Epoch 00122: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0077 - mse: 0.0077 - mae: 0.0697 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1460 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 123/500

Epoch 00123: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0671 - val_loss: 0.0337 - val_mse: 0.0337 - val_mae: 0.1460 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 124/500

Epoch 00124: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0684 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1458 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 125/500

Epoch 00125: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0678 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1456 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 126/500

Epoch 00126: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0084 - mse: 0.0084 - mae: 0.0726 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1457 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 127/500

Epoch 00127: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0678 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1456 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 128/500

Epoch 00128: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0688 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1456 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 129/500

Epoch 00129: val_loss did not improve from 0.03352
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0662 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1456 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 130/500

Epoch 00130: val_loss improved from 0.03352 to 0.03350, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0708 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1455 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 131/500

Epoch 00131: val_loss did not improve from 0.03350
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0639 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1455 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 132/500

Epoch 00132: val_loss improved from 0.03350 to 0.03347, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0718 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1454 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 133/500

Epoch 00133: val_loss did not improve from 0.03347
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0703 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1457 - lr: 1.0000e-05 - 74ms/epoch - 5ms/step
Epoch 134/500

Epoch 00134: val_loss did not improve from 0.03347
16/16 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0661 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1456 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 135/500

Epoch 00135: val_loss improved from 0.03347 to 0.03346, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0656 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1455 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 136/500

Epoch 00136: val_loss improved from 0.03346 to 0.03336, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0683 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1452 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 137/500

Epoch 00137: val_loss improved from 0.03336 to 0.03328, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0695 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1450 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 138/500

Epoch 00138: val_loss improved from 0.03328 to 0.03321, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0087 - mse: 0.0087 - mae: 0.0741 - val_loss: 0.0332 - val_mse: 0.0332 - val_mae: 0.1449 - lr: 1.0000e-05 - 118ms/epoch - 7ms/step
Epoch 139/500

Epoch 00139: val_loss improved from 0.03321 to 0.03318, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0634 - val_loss: 0.0332 - val_mse: 0.0332 - val_mae: 0.1448 - lr: 1.0000e-05 - 111ms/epoch - 7ms/step
Epoch 140/500

Epoch 00140: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0656 - val_loss: 0.0332 - val_mse: 0.0332 - val_mae: 0.1450 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 141/500

Epoch 00141: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0631 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1451 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 142/500

Epoch 00142: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0663 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1454 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 143/500

Epoch 00143: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0672 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1455 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 144/500

Epoch 00144: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0709 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1456 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 145/500

Epoch 00145: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0682 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1456 - lr: 1.0000e-05 - 74ms/epoch - 5ms/step
Epoch 146/500

Epoch 00146: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0680 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1458 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 147/500

Epoch 00147: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0637 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1460 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 148/500

Epoch 00148: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0646 - val_loss: 0.0336 - val_mse: 0.0336 - val_mae: 0.1461 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 149/500

Epoch 00149: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0663 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1459 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 150/500

Epoch 00150: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0662 - val_loss: 0.0335 - val_mse: 0.0335 - val_mae: 0.1458 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 151/500

Epoch 00151: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0651 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1455 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 152/500

Epoch 00152: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0653 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1455 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 153/500

Epoch 00153: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0688 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1454 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 154/500

Epoch 00154: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0669 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1456 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 155/500

Epoch 00155: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0637 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1458 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 156/500

Epoch 00156: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0692 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1458 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 157/500

Epoch 00157: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0081 - mse: 0.0081 - mae: 0.0701 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1455 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 158/500

Epoch 00158: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0655 - val_loss: 0.0332 - val_mse: 0.0332 - val_mae: 0.1453 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 159/500

Epoch 00159: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0665 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1455 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 160/500

Epoch 00160: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0652 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1458 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 161/500

Epoch 00161: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0685 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1456 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 162/500

Epoch 00162: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0683 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1456 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 163/500

Epoch 00163: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0663 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1458 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 164/500

Epoch 00164: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0674 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1458 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 165/500

Epoch 00165: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0679 - val_loss: 0.0334 - val_mse: 0.0334 - val_mae: 0.1459 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 166/500

Epoch 00166: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0678 - val_loss: 0.0332 - val_mse: 0.0332 - val_mae: 0.1455 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 167/500

Epoch 00167: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0665 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1457 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 168/500

Epoch 00168: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0673 - val_loss: 0.0333 - val_mse: 0.0333 - val_mae: 0.1457 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 169/500

Epoch 00169: val_loss did not improve from 0.03318
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0655 - val_loss: 0.0332 - val_mse: 0.0332 - val_mae: 0.1456 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 170/500

Epoch 00170: val_loss improved from 0.03318 to 0.03314, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0683 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1454 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 171/500

Epoch 00171: val_loss improved from 0.03314 to 0.03308, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0646 - val_loss: 0.0331 - val_mse: 0.0331 - val_mae: 0.1452 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 172/500

Epoch 00172: val_loss improved from 0.03308 to 0.03294, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0662 - val_loss: 0.0329 - val_mse: 0.0329 - val_mae: 0.1448 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 173/500

Epoch 00173: val_loss improved from 0.03294 to 0.03271, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0669 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1442 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 174/500

Epoch 00174: val_loss improved from 0.03271 to 0.03261, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0659 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1440 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 175/500

Epoch 00175: val_loss did not improve from 0.03261
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0641 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1442 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 176/500

Epoch 00176: val_loss did not improve from 0.03261
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0653 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1443 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 177/500

Epoch 00177: val_loss did not improve from 0.03261
16/16 - 0s - loss: 0.0076 - mse: 0.0076 - mae: 0.0685 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1442 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 178/500

Epoch 00178: val_loss did not improve from 0.03261
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0639 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1443 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 179/500

Epoch 00179: val_loss did not improve from 0.03261
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0622 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1442 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 180/500

Epoch 00180: val_loss improved from 0.03261 to 0.03253, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0639 - val_loss: 0.0325 - val_mse: 0.0325 - val_mae: 0.1439 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 181/500

Epoch 00181: val_loss improved from 0.03253 to 0.03239, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0658 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1435 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 182/500

Epoch 00182: val_loss improved from 0.03239 to 0.03237, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0661 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1435 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 183/500

Epoch 00183: val_loss improved from 0.03237 to 0.03219, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0667 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1430 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 184/500

Epoch 00184: val_loss improved from 0.03219 to 0.03213, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0641 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1429 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 185/500

Epoch 00185: val_loss improved from 0.03213 to 0.03205, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0654 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1427 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 186/500

Epoch 00186: val_loss improved from 0.03205 to 0.03193, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0667 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1423 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 187/500

Epoch 00187: val_loss improved from 0.03193 to 0.03192, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0659 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1423 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 188/500

Epoch 00188: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0671 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1425 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 189/500

Epoch 00189: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0666 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1428 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 190/500

Epoch 00190: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0631 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1430 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 191/500

Epoch 00191: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0075 - mse: 0.0075 - mae: 0.0673 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1432 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 192/500

Epoch 00192: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0640 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1436 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 193/500

Epoch 00193: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0659 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1438 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 194/500

Epoch 00194: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0073 - mse: 0.0073 - mae: 0.0672 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1438 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 195/500

Epoch 00195: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0664 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1439 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 196/500

Epoch 00196: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0656 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1438 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 197/500

Epoch 00197: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0618 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1435 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 198/500

Epoch 00198: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0653 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1435 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 199/500

Epoch 00199: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0623 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1438 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 200/500

Epoch 00200: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0656 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1439 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 201/500

Epoch 00201: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0653 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1441 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 202/500

Epoch 00202: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0657 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1441 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 203/500

Epoch 00203: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0639 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1440 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 204/500

Epoch 00204: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0648 - val_loss: 0.0325 - val_mse: 0.0325 - val_mae: 0.1443 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 205/500

Epoch 00205: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0652 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1447 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 206/500

Epoch 00206: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0632 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1448 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 207/500

Epoch 00207: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0646 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1449 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 208/500

Epoch 00208: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0638 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1452 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 209/500

Epoch 00209: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0660 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1452 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 210/500

Epoch 00210: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0688 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1449 - lr: 1.0000e-05 - 74ms/epoch - 5ms/step
Epoch 211/500

Epoch 00211: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0641 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1448 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 212/500

Epoch 00212: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0651 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1453 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 213/500

Epoch 00213: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0628 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1453 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 214/500

Epoch 00214: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0634 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1452 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 215/500

Epoch 00215: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0624 - val_loss: 0.0327 - val_mse: 0.0327 - val_mae: 0.1453 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 216/500

Epoch 00216: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0644 - val_loss: 0.0326 - val_mse: 0.0326 - val_mae: 0.1449 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 217/500

Epoch 00217: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0639 - val_loss: 0.0324 - val_mse: 0.0324 - val_mae: 0.1443 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 218/500

Epoch 00218: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0621 - val_loss: 0.0323 - val_mse: 0.0323 - val_mae: 0.1443 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 219/500

Epoch 00219: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0633 - val_loss: 0.0322 - val_mse: 0.0322 - val_mae: 0.1439 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 220/500

Epoch 00220: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0634 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1434 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 221/500

Epoch 00221: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0639 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1434 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 222/500

Epoch 00222: val_loss did not improve from 0.03192
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0634 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1434 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 223/500

Epoch 00223: val_loss improved from 0.03192 to 0.03191, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0625 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1433 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 224/500

Epoch 00224: val_loss improved from 0.03191 to 0.03190, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0650 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1433 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 225/500

Epoch 00225: val_loss did not improve from 0.03190
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0619 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1434 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 226/500

Epoch 00226: val_loss did not improve from 0.03190
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0630 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1434 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 227/500

Epoch 00227: val_loss improved from 0.03190 to 0.03186, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0626 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1432 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 228/500

Epoch 00228: val_loss improved from 0.03186 to 0.03178, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0069 - mse: 0.0069 - mae: 0.0650 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1430 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 229/500

Epoch 00229: val_loss did not improve from 0.03178
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0630 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1433 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 230/500

Epoch 00230: val_loss did not improve from 0.03178
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0602 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1439 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 231/500

Epoch 00231: val_loss did not improve from 0.03178
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0643 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1439 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 232/500

Epoch 00232: val_loss did not improve from 0.03178
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0621 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1436 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 233/500

Epoch 00233: val_loss did not improve from 0.03178
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0582 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1437 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 234/500

Epoch 00234: val_loss did not improve from 0.03178
16/16 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0642 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1436 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 235/500

Epoch 00235: val_loss did not improve from 0.03178
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0650 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1437 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 236/500

Epoch 00236: val_loss did not improve from 0.03178
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0652 - val_loss: 0.0321 - val_mse: 0.0321 - val_mae: 0.1441 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 237/500

Epoch 00237: val_loss did not improve from 0.03178
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0615 - val_loss: 0.0320 - val_mse: 0.0320 - val_mae: 0.1440 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 238/500

Epoch 00238: val_loss did not improve from 0.03178
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0654 - val_loss: 0.0319 - val_mse: 0.0319 - val_mae: 0.1435 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 239/500

Epoch 00239: val_loss did not improve from 0.03178
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0606 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1435 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 240/500

Epoch 00240: val_loss did not improve from 0.03178
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0647 - val_loss: 0.0318 - val_mse: 0.0318 - val_mae: 0.1434 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 241/500

Epoch 00241: val_loss improved from 0.03178 to 0.03168, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0619 - val_loss: 0.0317 - val_mse: 0.0317 - val_mae: 0.1431 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 242/500

Epoch 00242: val_loss improved from 0.03168 to 0.03161, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0627 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1429 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 243/500

Epoch 00243: val_loss did not improve from 0.03161
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0621 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1430 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 244/500

Epoch 00244: val_loss improved from 0.03161 to 0.03161, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0634 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1430 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 245/500

Epoch 00245: val_loss improved from 0.03161 to 0.03150, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0071 - mse: 0.0071 - mae: 0.0661 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1428 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 246/500

Epoch 00246: val_loss improved from 0.03150 to 0.03136, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0631 - val_loss: 0.0314 - val_mse: 0.0314 - val_mae: 0.1424 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 247/500

Epoch 00247: val_loss improved from 0.03136 to 0.03122, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0643 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1420 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 248/500

Epoch 00248: val_loss did not improve from 0.03122
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0625 - val_loss: 0.0314 - val_mse: 0.0314 - val_mae: 0.1425 - lr: 1.0000e-05 - 125ms/epoch - 8ms/step
Epoch 249/500

Epoch 00249: val_loss did not improve from 0.03122
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0638 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1429 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 250/500

Epoch 00250: val_loss did not improve from 0.03122
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0624 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1429 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 251/500

Epoch 00251: val_loss did not improve from 0.03122
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0638 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1428 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 252/500

Epoch 00252: val_loss did not improve from 0.03122
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0627 - val_loss: 0.0313 - val_mse: 0.0313 - val_mae: 0.1423 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 253/500

Epoch 00253: val_loss improved from 0.03122 to 0.03121, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0068 - mse: 0.0068 - mae: 0.0659 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1421 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 254/500

Epoch 00254: val_loss did not improve from 0.03121
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0615 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1421 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 255/500

Epoch 00255: val_loss improved from 0.03121 to 0.03116, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0617 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1420 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 256/500

Epoch 00256: val_loss improved from 0.03116 to 0.03108, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0614 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1417 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 257/500

Epoch 00257: val_loss improved from 0.03108 to 0.03100, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0594 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1416 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 258/500

Epoch 00258: val_loss improved from 0.03100 to 0.03095, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0613 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1415 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 259/500

Epoch 00259: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0638 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1417 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 260/500

Epoch 00260: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0065 - mse: 0.0065 - mae: 0.0627 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1416 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 261/500

Epoch 00261: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0669 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1417 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 262/500

Epoch 00262: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0622 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1423 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 263/500

Epoch 00263: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0614 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1431 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 264/500

Epoch 00264: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0610 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1433 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 265/500

Epoch 00265: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0608 - val_loss: 0.0316 - val_mse: 0.0316 - val_mae: 0.1433 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 266/500

Epoch 00266: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0619 - val_loss: 0.0315 - val_mse: 0.0315 - val_mae: 0.1432 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 267/500

Epoch 00267: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0601 - val_loss: 0.0314 - val_mse: 0.0314 - val_mae: 0.1429 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 268/500

Epoch 00268: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0600 - val_loss: 0.0312 - val_mse: 0.0312 - val_mae: 0.1424 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 269/500

Epoch 00269: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0613 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1423 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 270/500

Epoch 00270: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0561 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1423 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 271/500

Epoch 00271: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0643 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1420 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 272/500

Epoch 00272: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0616 - val_loss: 0.0310 - val_mse: 0.0310 - val_mae: 0.1421 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 273/500

Epoch 00273: val_loss did not improve from 0.03095
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0593 - val_loss: 0.0311 - val_mse: 0.0311 - val_mae: 0.1423 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 274/500

Epoch 00274: val_loss improved from 0.03095 to 0.03077, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0603 - val_loss: 0.0308 - val_mse: 0.0308 - val_mae: 0.1414 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 275/500

Epoch 00275: val_loss improved from 0.03077 to 0.03056, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0612 - val_loss: 0.0306 - val_mse: 0.0306 - val_mae: 0.1408 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 276/500

Epoch 00276: val_loss improved from 0.03056 to 0.03049, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0613 - val_loss: 0.0305 - val_mse: 0.0305 - val_mae: 0.1406 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 277/500

Epoch 00277: val_loss did not improve from 0.03049
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0616 - val_loss: 0.0305 - val_mse: 0.0305 - val_mae: 0.1407 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 278/500

Epoch 00278: val_loss improved from 0.03049 to 0.03033, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0624 - val_loss: 0.0303 - val_mse: 0.0303 - val_mae: 0.1402 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 279/500

Epoch 00279: val_loss improved from 0.03033 to 0.03008, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0620 - val_loss: 0.0301 - val_mse: 0.0301 - val_mae: 0.1396 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 280/500

Epoch 00280: val_loss improved from 0.03008 to 0.03007, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0610 - val_loss: 0.0301 - val_mse: 0.0301 - val_mae: 0.1396 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 281/500

Epoch 00281: val_loss did not improve from 0.03007
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0605 - val_loss: 0.0302 - val_mse: 0.0302 - val_mae: 0.1399 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 282/500

Epoch 00282: val_loss did not improve from 0.03007
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0647 - val_loss: 0.0302 - val_mse: 0.0302 - val_mae: 0.1399 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 283/500

Epoch 00283: val_loss improved from 0.03007 to 0.02989, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0619 - val_loss: 0.0299 - val_mse: 0.0299 - val_mae: 0.1392 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 284/500

Epoch 00284: val_loss improved from 0.02989 to 0.02979, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0612 - val_loss: 0.0298 - val_mse: 0.0298 - val_mae: 0.1389 - lr: 1.0000e-05 - 130ms/epoch - 8ms/step
Epoch 285/500

Epoch 00285: val_loss improved from 0.02979 to 0.02966, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0600 - val_loss: 0.0297 - val_mse: 0.0297 - val_mae: 0.1386 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 286/500

Epoch 00286: val_loss improved from 0.02966 to 0.02951, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0595 - val_loss: 0.0295 - val_mse: 0.0295 - val_mae: 0.1382 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 287/500

Epoch 00287: val_loss improved from 0.02951 to 0.02924, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0625 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1374 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 288/500

Epoch 00288: val_loss improved from 0.02924 to 0.02917, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0064 - mse: 0.0064 - mae: 0.0626 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1372 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 289/500

Epoch 00289: val_loss improved from 0.02917 to 0.02916, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0599 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1372 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 290/500

Epoch 00290: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0608 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1373 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 291/500

Epoch 00291: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0585 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1373 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 292/500

Epoch 00292: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0593 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1373 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 293/500

Epoch 00293: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0590 - val_loss: 0.0294 - val_mse: 0.0294 - val_mae: 0.1380 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 294/500

Epoch 00294: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0608 - val_loss: 0.0294 - val_mse: 0.0294 - val_mae: 0.1381 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 295/500

Epoch 00295: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0584 - val_loss: 0.0294 - val_mse: 0.0294 - val_mae: 0.1382 - lr: 1.0000e-05 - 77ms/epoch - 5ms/step
Epoch 296/500

Epoch 00296: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0605 - val_loss: 0.0296 - val_mse: 0.0296 - val_mae: 0.1386 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 297/500

Epoch 00297: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0609 - val_loss: 0.0295 - val_mse: 0.0295 - val_mae: 0.1383 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 298/500

Epoch 00298: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0590 - val_loss: 0.0296 - val_mse: 0.0296 - val_mae: 0.1386 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 299/500

Epoch 00299: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0603 - val_loss: 0.0297 - val_mse: 0.0297 - val_mae: 0.1390 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 300/500

Epoch 00300: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0066 - mse: 0.0066 - mae: 0.0637 - val_loss: 0.0296 - val_mse: 0.0296 - val_mae: 0.1388 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 301/500

Epoch 00301: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0591 - val_loss: 0.0293 - val_mse: 0.0293 - val_mae: 0.1382 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 302/500

Epoch 00302: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0611 - val_loss: 0.0294 - val_mse: 0.0294 - val_mae: 0.1384 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 303/500

Epoch 00303: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0613 - val_loss: 0.0296 - val_mse: 0.0296 - val_mae: 0.1388 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 304/500

Epoch 00304: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0613 - val_loss: 0.0295 - val_mse: 0.0295 - val_mae: 0.1386 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 305/500

Epoch 00305: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0619 - val_loss: 0.0295 - val_mse: 0.0295 - val_mae: 0.1388 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 306/500

Epoch 00306: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0601 - val_loss: 0.0295 - val_mse: 0.0295 - val_mae: 0.1388 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 307/500

Epoch 00307: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0600 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1380 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 308/500

Epoch 00308: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0599 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1379 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 309/500

Epoch 00309: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0599 - val_loss: 0.0292 - val_mse: 0.0292 - val_mae: 0.1378 - lr: 1.0000e-05 - 73ms/epoch - 5ms/step
Epoch 310/500

Epoch 00310: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0589 - val_loss: 0.0293 - val_mse: 0.0293 - val_mae: 0.1381 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 311/500

Epoch 00311: val_loss did not improve from 0.02916
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0602 - val_loss: 0.0293 - val_mse: 0.0293 - val_mae: 0.1381 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 312/500

Epoch 00312: val_loss improved from 0.02916 to 0.02910, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0587 - val_loss: 0.0291 - val_mse: 0.0291 - val_mae: 0.1375 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 313/500

Epoch 00313: val_loss improved from 0.02910 to 0.02891, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0607 - val_loss: 0.0289 - val_mse: 0.0289 - val_mae: 0.1370 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 314/500

Epoch 00314: val_loss improved from 0.02891 to 0.02882, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0593 - val_loss: 0.0288 - val_mse: 0.0288 - val_mae: 0.1368 - lr: 1.0000e-05 - 116ms/epoch - 7ms/step
Epoch 315/500

Epoch 00315: val_loss improved from 0.02882 to 0.02868, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0642 - val_loss: 0.0287 - val_mse: 0.0287 - val_mae: 0.1364 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 316/500

Epoch 00316: val_loss improved from 0.02868 to 0.02857, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0588 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1361 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 317/500

Epoch 00317: val_loss did not improve from 0.02857
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0602 - val_loss: 0.0287 - val_mse: 0.0287 - val_mae: 0.1364 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 318/500

Epoch 00318: val_loss did not improve from 0.02857
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0602 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1362 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 319/500

Epoch 00319: val_loss did not improve from 0.02857
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0586 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1363 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 320/500

Epoch 00320: val_loss did not improve from 0.02857
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0608 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1363 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 321/500

Epoch 00321: val_loss improved from 0.02857 to 0.02848, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0619 - val_loss: 0.0285 - val_mse: 0.0285 - val_mae: 0.1361 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 322/500

Epoch 00322: val_loss did not improve from 0.02848
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0580 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1363 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 323/500

Epoch 00323: val_loss did not improve from 0.02848
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0595 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1364 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 324/500

Epoch 00324: val_loss did not improve from 0.02848
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0570 - val_loss: 0.0285 - val_mse: 0.0285 - val_mae: 0.1363 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 325/500

Epoch 00325: val_loss improved from 0.02848 to 0.02838, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0605 - val_loss: 0.0284 - val_mse: 0.0284 - val_mae: 0.1358 - lr: 1.0000e-05 - 121ms/epoch - 8ms/step
Epoch 326/500

Epoch 00326: val_loss improved from 0.02838 to 0.02836, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0586 - val_loss: 0.0284 - val_mse: 0.0284 - val_mae: 0.1358 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 327/500

Epoch 00327: val_loss did not improve from 0.02836
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0581 - val_loss: 0.0285 - val_mse: 0.0285 - val_mae: 0.1362 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 328/500

Epoch 00328: val_loss did not improve from 0.02836
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0570 - val_loss: 0.0285 - val_mse: 0.0285 - val_mae: 0.1362 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 329/500

Epoch 00329: val_loss improved from 0.02836 to 0.02826, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0597 - val_loss: 0.0283 - val_mse: 0.0283 - val_mae: 0.1356 - lr: 1.0000e-05 - 107ms/epoch - 7ms/step
Epoch 330/500

Epoch 00330: val_loss did not improve from 0.02826
16/16 - 0s - loss: 0.0061 - mse: 0.0061 - mae: 0.0611 - val_loss: 0.0283 - val_mse: 0.0283 - val_mae: 0.1358 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 331/500

Epoch 00331: val_loss did not improve from 0.02826
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0603 - val_loss: 0.0285 - val_mse: 0.0285 - val_mae: 0.1364 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 332/500

Epoch 00332: val_loss did not improve from 0.02826
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0597 - val_loss: 0.0286 - val_mse: 0.0286 - val_mae: 0.1367 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 333/500

Epoch 00333: val_loss did not improve from 0.02826
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0599 - val_loss: 0.0285 - val_mse: 0.0285 - val_mae: 0.1364 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 334/500

Epoch 00334: val_loss did not improve from 0.02826
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0578 - val_loss: 0.0283 - val_mse: 0.0283 - val_mae: 0.1360 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 335/500

Epoch 00335: val_loss did not improve from 0.02826
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0573 - val_loss: 0.0283 - val_mse: 0.0283 - val_mae: 0.1358 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 336/500

Epoch 00336: val_loss improved from 0.02826 to 0.02824, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0569 - val_loss: 0.0282 - val_mse: 0.0282 - val_mae: 0.1358 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 337/500

Epoch 00337: val_loss improved from 0.02824 to 0.02795, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0595 - val_loss: 0.0279 - val_mse: 0.0279 - val_mae: 0.1350 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 338/500

Epoch 00338: val_loss improved from 0.02795 to 0.02794, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0591 - val_loss: 0.0279 - val_mse: 0.0279 - val_mae: 0.1350 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 339/500

Epoch 00339: val_loss did not improve from 0.02794
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0576 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1352 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 340/500

Epoch 00340: val_loss did not improve from 0.02794
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0578 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1356 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 341/500

Epoch 00341: val_loss did not improve from 0.02794
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0570 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1355 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 342/500

Epoch 00342: val_loss did not improve from 0.02794
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0583 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1355 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 343/500

Epoch 00343: val_loss did not improve from 0.02794
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0579 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1356 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 344/500

Epoch 00344: val_loss did not improve from 0.02794
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0598 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1352 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 345/500

Epoch 00345: val_loss improved from 0.02794 to 0.02793, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0568 - val_loss: 0.0279 - val_mse: 0.0279 - val_mae: 0.1351 - lr: 1.0000e-05 - 116ms/epoch - 7ms/step
Epoch 346/500

Epoch 00346: val_loss did not improve from 0.02793
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0594 - val_loss: 0.0280 - val_mse: 0.0280 - val_mae: 0.1353 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 347/500

Epoch 00347: val_loss did not improve from 0.02793
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0568 - val_loss: 0.0281 - val_mse: 0.0281 - val_mae: 0.1356 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 348/500

Epoch 00348: val_loss improved from 0.02793 to 0.02792, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0597 - val_loss: 0.0279 - val_mse: 0.0279 - val_mae: 0.1352 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 349/500

Epoch 00349: val_loss improved from 0.02792 to 0.02786, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0577 - val_loss: 0.0279 - val_mse: 0.0279 - val_mae: 0.1350 - lr: 1.0000e-05 - 118ms/epoch - 7ms/step
Epoch 350/500

Epoch 00350: val_loss improved from 0.02786 to 0.02780, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0567 - val_loss: 0.0278 - val_mse: 0.0278 - val_mae: 0.1348 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 351/500

Epoch 00351: val_loss improved from 0.02780 to 0.02757, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0554 - val_loss: 0.0276 - val_mse: 0.0276 - val_mae: 0.1341 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 352/500

Epoch 00352: val_loss improved from 0.02757 to 0.02746, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0595 - val_loss: 0.0275 - val_mse: 0.0275 - val_mae: 0.1338 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 353/500

Epoch 00353: val_loss improved from 0.02746 to 0.02734, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0575 - val_loss: 0.0273 - val_mse: 0.0273 - val_mae: 0.1335 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 354/500

Epoch 00354: val_loss improved from 0.02734 to 0.02710, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0575 - val_loss: 0.0271 - val_mse: 0.0271 - val_mae: 0.1328 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 355/500

Epoch 00355: val_loss improved from 0.02710 to 0.02709, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0576 - val_loss: 0.0271 - val_mse: 0.0271 - val_mae: 0.1329 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 356/500

Epoch 00356: val_loss did not improve from 0.02709
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0602 - val_loss: 0.0271 - val_mse: 0.0271 - val_mae: 0.1330 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 357/500

Epoch 00357: val_loss did not improve from 0.02709
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0589 - val_loss: 0.0272 - val_mse: 0.0272 - val_mae: 0.1333 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 358/500

Epoch 00358: val_loss did not improve from 0.02709
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0576 - val_loss: 0.0272 - val_mse: 0.0272 - val_mae: 0.1334 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 359/500

Epoch 00359: val_loss did not improve from 0.02709
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0601 - val_loss: 0.0272 - val_mse: 0.0272 - val_mae: 0.1332 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 360/500

Epoch 00360: val_loss improved from 0.02709 to 0.02703, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0060 - mse: 0.0060 - mae: 0.0599 - val_loss: 0.0270 - val_mse: 0.0270 - val_mae: 0.1328 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 361/500

Epoch 00361: val_loss improved from 0.02703 to 0.02695, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0573 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1326 - lr: 1.0000e-05 - 115ms/epoch - 7ms/step
Epoch 362/500

Epoch 00362: val_loss improved from 0.02695 to 0.02691, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0564 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1325 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 363/500

Epoch 00363: val_loss did not improve from 0.02691
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0579 - val_loss: 0.0270 - val_mse: 0.0270 - val_mae: 0.1327 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 364/500

Epoch 00364: val_loss did not improve from 0.02691
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0582 - val_loss: 0.0271 - val_mse: 0.0271 - val_mae: 0.1330 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 365/500

Epoch 00365: val_loss did not improve from 0.02691
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0597 - val_loss: 0.0272 - val_mse: 0.0272 - val_mae: 0.1334 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 366/500

Epoch 00366: val_loss did not improve from 0.02691
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0550 - val_loss: 0.0272 - val_mse: 0.0272 - val_mae: 0.1336 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 367/500

Epoch 00367: val_loss did not improve from 0.02691
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0572 - val_loss: 0.0271 - val_mse: 0.0271 - val_mae: 0.1333 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 368/500

Epoch 00368: val_loss did not improve from 0.02691
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0591 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1327 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 369/500

Epoch 00369: val_loss did not improve from 0.02691
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0586 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1327 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 370/500

Epoch 00370: val_loss improved from 0.02691 to 0.02685, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0582 - val_loss: 0.0269 - val_mse: 0.0269 - val_mae: 0.1325 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 371/500

Epoch 00371: val_loss improved from 0.02685 to 0.02660, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0568 - val_loss: 0.0266 - val_mse: 0.0266 - val_mae: 0.1317 - lr: 1.0000e-05 - 121ms/epoch - 8ms/step
Epoch 372/500

Epoch 00372: val_loss improved from 0.02660 to 0.02651, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0058 - mse: 0.0058 - mae: 0.0605 - val_loss: 0.0265 - val_mse: 0.0265 - val_mae: 0.1315 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 373/500

Epoch 00373: val_loss improved from 0.02651 to 0.02637, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0571 - val_loss: 0.0264 - val_mse: 0.0264 - val_mae: 0.1311 - lr: 1.0000e-05 - 110ms/epoch - 7ms/step
Epoch 374/500

Epoch 00374: val_loss did not improve from 0.02637
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0571 - val_loss: 0.0264 - val_mse: 0.0264 - val_mae: 0.1312 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 375/500

Epoch 00375: val_loss improved from 0.02637 to 0.02636, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0588 - val_loss: 0.0264 - val_mse: 0.0264 - val_mae: 0.1311 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 376/500

Epoch 00376: val_loss improved from 0.02636 to 0.02627, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0578 - val_loss: 0.0263 - val_mse: 0.0263 - val_mae: 0.1309 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 377/500

Epoch 00377: val_loss did not improve from 0.02627
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0551 - val_loss: 0.0263 - val_mse: 0.0263 - val_mae: 0.1311 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 378/500

Epoch 00378: val_loss improved from 0.02627 to 0.02616, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0584 - val_loss: 0.0262 - val_mse: 0.0262 - val_mae: 0.1306 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 379/500

Epoch 00379: val_loss did not improve from 0.02616
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0552 - val_loss: 0.0262 - val_mse: 0.0262 - val_mae: 0.1307 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 380/500

Epoch 00380: val_loss improved from 0.02616 to 0.02615, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0556 - val_loss: 0.0262 - val_mse: 0.0262 - val_mae: 0.1306 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 381/500

Epoch 00381: val_loss improved from 0.02615 to 0.02593, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0568 - val_loss: 0.0259 - val_mse: 0.0259 - val_mae: 0.1299 - lr: 1.0000e-05 - 119ms/epoch - 7ms/step
Epoch 382/500

Epoch 00382: val_loss did not improve from 0.02593
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0587 - val_loss: 0.0260 - val_mse: 0.0260 - val_mae: 0.1300 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 383/500

Epoch 00383: val_loss did not improve from 0.02593
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0586 - val_loss: 0.0260 - val_mse: 0.0260 - val_mae: 0.1301 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 384/500

Epoch 00384: val_loss improved from 0.02593 to 0.02583, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0597 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1297 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 385/500

Epoch 00385: val_loss improved from 0.02583 to 0.02577, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0562 - val_loss: 0.0258 - val_mse: 0.0258 - val_mae: 0.1295 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 386/500

Epoch 00386: val_loss improved from 0.02577 to 0.02556, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0580 - val_loss: 0.0256 - val_mse: 0.0256 - val_mae: 0.1288 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 387/500

Epoch 00387: val_loss improved from 0.02556 to 0.02552, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0565 - val_loss: 0.0255 - val_mse: 0.0255 - val_mae: 0.1288 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 388/500

Epoch 00388: val_loss improved from 0.02552 to 0.02527, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0547 - val_loss: 0.0253 - val_mse: 0.0253 - val_mae: 0.1280 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 389/500

Epoch 00389: val_loss improved from 0.02527 to 0.02519, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0559 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1278 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 390/500

Epoch 00390: val_loss did not improve from 0.02519
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0563 - val_loss: 0.0253 - val_mse: 0.0253 - val_mae: 0.1281 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 391/500

Epoch 00391: val_loss did not improve from 0.02519
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0566 - val_loss: 0.0255 - val_mse: 0.0255 - val_mae: 0.1287 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 392/500

Epoch 00392: val_loss did not improve from 0.02519
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0582 - val_loss: 0.0256 - val_mse: 0.0256 - val_mae: 0.1293 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 393/500

Epoch 00393: val_loss did not improve from 0.02519
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0568 - val_loss: 0.0256 - val_mse: 0.0256 - val_mae: 0.1293 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 394/500

Epoch 00394: val_loss did not improve from 0.02519
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0586 - val_loss: 0.0256 - val_mse: 0.0256 - val_mae: 0.1291 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 395/500

Epoch 00395: val_loss did not improve from 0.02519
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0562 - val_loss: 0.0255 - val_mse: 0.0255 - val_mae: 0.1290 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 396/500

Epoch 00396: val_loss did not improve from 0.02519
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0559 - val_loss: 0.0253 - val_mse: 0.0253 - val_mae: 0.1283 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 397/500

Epoch 00397: val_loss improved from 0.02519 to 0.02519, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0544 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1281 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 398/500

Epoch 00398: val_loss did not improve from 0.02519
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0565 - val_loss: 0.0253 - val_mse: 0.0253 - val_mae: 0.1284 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 399/500

Epoch 00399: val_loss did not improve from 0.02519
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0554 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1282 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 400/500

Epoch 00400: val_loss improved from 0.02519 to 0.02503, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0558 - val_loss: 0.0250 - val_mse: 0.0250 - val_mae: 0.1277 - lr: 1.0000e-05 - 122ms/epoch - 8ms/step
Epoch 401/500

Epoch 00401: val_loss improved from 0.02503 to 0.02499, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0577 - val_loss: 0.0250 - val_mse: 0.0250 - val_mae: 0.1276 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 402/500

Epoch 00402: val_loss did not improve from 0.02499
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0550 - val_loss: 0.0251 - val_mse: 0.0251 - val_mae: 0.1280 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 403/500

Epoch 00403: val_loss improved from 0.02499 to 0.02495, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0545 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1275 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 404/500

Epoch 00404: val_loss improved from 0.02495 to 0.02491, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0588 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1275 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 405/500

Epoch 00405: val_loss did not improve from 0.02491
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0562 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1277 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 406/500

Epoch 00406: val_loss did not improve from 0.02491
16/16 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0592 - val_loss: 0.0251 - val_mse: 0.0251 - val_mae: 0.1281 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 407/500

Epoch 00407: val_loss did not improve from 0.02491
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0579 - val_loss: 0.0251 - val_mse: 0.0251 - val_mae: 0.1280 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 408/500

Epoch 00408: val_loss did not improve from 0.02491
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0531 - val_loss: 0.0250 - val_mse: 0.0250 - val_mae: 0.1280 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 409/500

Epoch 00409: val_loss improved from 0.02491 to 0.02490, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0554 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1275 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 410/500

Epoch 00410: val_loss improved from 0.02490 to 0.02485, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0550 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1274 - lr: 1.0000e-05 - 106ms/epoch - 7ms/step
Epoch 411/500

Epoch 00411: val_loss improved from 0.02485 to 0.02478, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0564 - val_loss: 0.0248 - val_mse: 0.0248 - val_mae: 0.1271 - lr: 1.0000e-05 - 136ms/epoch - 8ms/step
Epoch 412/500

Epoch 00412: val_loss improved from 0.02478 to 0.02457, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0580 - val_loss: 0.0246 - val_mse: 0.0246 - val_mae: 0.1265 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 413/500

Epoch 00413: val_loss improved from 0.02457 to 0.02433, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0572 - val_loss: 0.0243 - val_mse: 0.0243 - val_mae: 0.1258 - lr: 1.0000e-05 - 118ms/epoch - 7ms/step
Epoch 414/500

Epoch 00414: val_loss improved from 0.02433 to 0.02427, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0551 - val_loss: 0.0243 - val_mse: 0.0243 - val_mae: 0.1256 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 415/500

Epoch 00415: val_loss improved from 0.02427 to 0.02416, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0576 - val_loss: 0.0242 - val_mse: 0.0242 - val_mae: 0.1252 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 416/500

Epoch 00416: val_loss improved from 0.02416 to 0.02416, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0567 - val_loss: 0.0242 - val_mse: 0.0242 - val_mae: 0.1252 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 417/500

Epoch 00417: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0525 - val_loss: 0.0244 - val_mse: 0.0244 - val_mae: 0.1260 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 418/500

Epoch 00418: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0540 - val_loss: 0.0246 - val_mse: 0.0246 - val_mae: 0.1267 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 419/500

Epoch 00419: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0562 - val_loss: 0.0246 - val_mse: 0.0246 - val_mae: 0.1268 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 420/500

Epoch 00420: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0537 - val_loss: 0.0248 - val_mse: 0.0248 - val_mae: 0.1275 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 421/500

Epoch 00421: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0537 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1286 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 422/500

Epoch 00422: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0560 - val_loss: 0.0251 - val_mse: 0.0251 - val_mae: 0.1286 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 423/500

Epoch 00423: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0565 - val_loss: 0.0251 - val_mse: 0.0251 - val_mae: 0.1285 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 424/500

Epoch 00424: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0043 - mse: 0.0043 - mae: 0.0523 - val_loss: 0.0251 - val_mse: 0.0251 - val_mae: 0.1285 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 425/500

Epoch 00425: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0574 - val_loss: 0.0252 - val_mse: 0.0252 - val_mae: 0.1288 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 426/500

Epoch 00426: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0550 - val_loss: 0.0250 - val_mse: 0.0250 - val_mae: 0.1282 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 427/500

Epoch 00427: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0556 - val_loss: 0.0250 - val_mse: 0.0250 - val_mae: 0.1283 - lr: 1.0000e-05 - 78ms/epoch - 5ms/step
Epoch 428/500

Epoch 00428: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0561 - val_loss: 0.0250 - val_mse: 0.0250 - val_mae: 0.1281 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 429/500

Epoch 00429: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0542 - val_loss: 0.0249 - val_mse: 0.0249 - val_mae: 0.1280 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 430/500

Epoch 00430: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0536 - val_loss: 0.0247 - val_mse: 0.0247 - val_mae: 0.1275 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 431/500

Epoch 00431: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0545 - val_loss: 0.0247 - val_mse: 0.0247 - val_mae: 0.1274 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 432/500

Epoch 00432: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0564 - val_loss: 0.0247 - val_mse: 0.0247 - val_mae: 0.1275 - lr: 1.0000e-05 - 76ms/epoch - 5ms/step
Epoch 433/500

Epoch 00433: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0540 - val_loss: 0.0248 - val_mse: 0.0248 - val_mae: 0.1278 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 434/500

Epoch 00434: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0547 - val_loss: 0.0247 - val_mse: 0.0247 - val_mae: 0.1275 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 435/500

Epoch 00435: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0557 - val_loss: 0.0247 - val_mse: 0.0247 - val_mae: 0.1273 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 436/500

Epoch 00436: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0549 - val_loss: 0.0245 - val_mse: 0.0245 - val_mae: 0.1268 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 437/500

Epoch 00437: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0553 - val_loss: 0.0244 - val_mse: 0.0244 - val_mae: 0.1264 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 438/500

Epoch 00438: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0557 - val_loss: 0.0243 - val_mse: 0.0243 - val_mae: 0.1262 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 439/500

Epoch 00439: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0578 - val_loss: 0.0243 - val_mse: 0.0243 - val_mae: 0.1263 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 440/500

Epoch 00440: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0547 - val_loss: 0.0245 - val_mse: 0.0245 - val_mae: 0.1268 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 441/500

Epoch 00441: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0550 - val_loss: 0.0244 - val_mse: 0.0244 - val_mae: 0.1267 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 442/500

Epoch 00442: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0541 - val_loss: 0.0245 - val_mse: 0.0245 - val_mae: 0.1269 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 443/500

Epoch 00443: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0552 - val_loss: 0.0245 - val_mse: 0.0245 - val_mae: 0.1269 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 444/500

Epoch 00444: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0563 - val_loss: 0.0243 - val_mse: 0.0243 - val_mae: 0.1265 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 445/500

Epoch 00445: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0530 - val_loss: 0.0242 - val_mse: 0.0242 - val_mae: 0.1262 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 446/500

Epoch 00446: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0560 - val_loss: 0.0243 - val_mse: 0.0243 - val_mae: 0.1264 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 447/500

Epoch 00447: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0563 - val_loss: 0.0243 - val_mse: 0.0243 - val_mae: 0.1265 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 448/500

Epoch 00448: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0558 - val_loss: 0.0242 - val_mse: 0.0242 - val_mae: 0.1261 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 449/500

Epoch 00449: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0533 - val_loss: 0.0242 - val_mse: 0.0242 - val_mae: 0.1260 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 450/500

Epoch 00450: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0564 - val_loss: 0.0242 - val_mse: 0.0242 - val_mae: 0.1262 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 451/500

Epoch 00451: val_loss did not improve from 0.02416
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0540 - val_loss: 0.0242 - val_mse: 0.0242 - val_mae: 0.1261 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 452/500

Epoch 00452: val_loss improved from 0.02416 to 0.02412, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0553 - val_loss: 0.0241 - val_mse: 0.0241 - val_mae: 0.1260 - lr: 1.0000e-05 - 114ms/epoch - 7ms/step
Epoch 453/500

Epoch 00453: val_loss improved from 0.02412 to 0.02397, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0534 - val_loss: 0.0240 - val_mse: 0.0240 - val_mae: 0.1256 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 454/500

Epoch 00454: val_loss improved from 0.02397 to 0.02385, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0556 - val_loss: 0.0238 - val_mse: 0.0238 - val_mae: 0.1252 - lr: 1.0000e-05 - 145ms/epoch - 9ms/step
Epoch 455/500

Epoch 00455: val_loss did not improve from 0.02385
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0550 - val_loss: 0.0240 - val_mse: 0.0240 - val_mae: 0.1255 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 456/500

Epoch 00456: val_loss did not improve from 0.02385
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0552 - val_loss: 0.0239 - val_mse: 0.0239 - val_mae: 0.1253 - lr: 1.0000e-05 - 75ms/epoch - 5ms/step
Epoch 457/500

Epoch 00457: val_loss improved from 0.02385 to 0.02369, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0576 - val_loss: 0.0237 - val_mse: 0.0237 - val_mae: 0.1248 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 458/500

Epoch 00458: val_loss improved from 0.02369 to 0.02366, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0553 - val_loss: 0.0237 - val_mse: 0.0237 - val_mae: 0.1246 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 459/500

Epoch 00459: val_loss improved from 0.02366 to 0.02365, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0544 - val_loss: 0.0236 - val_mse: 0.0236 - val_mae: 0.1246 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 460/500

Epoch 00460: val_loss improved from 0.02365 to 0.02351, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0536 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1242 - lr: 1.0000e-05 - 138ms/epoch - 9ms/step
Epoch 461/500

Epoch 00461: val_loss improved from 0.02351 to 0.02348, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0551 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1241 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 462/500

Epoch 00462: val_loss did not improve from 0.02348
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0541 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1241 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 463/500

Epoch 00463: val_loss improved from 0.02348 to 0.02339, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0546 - val_loss: 0.0234 - val_mse: 0.0234 - val_mae: 0.1238 - lr: 1.0000e-05 - 89ms/epoch - 6ms/step
Epoch 464/500

Epoch 00464: val_loss improved from 0.02339 to 0.02324, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0551 - val_loss: 0.0232 - val_mse: 0.0232 - val_mae: 0.1234 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 465/500

Epoch 00465: val_loss did not improve from 0.02324
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0549 - val_loss: 0.0233 - val_mse: 0.0233 - val_mae: 0.1235 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 466/500

Epoch 00466: val_loss improved from 0.02324 to 0.02314, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0542 - val_loss: 0.0231 - val_mse: 0.0231 - val_mae: 0.1231 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 467/500

Epoch 00467: val_loss improved from 0.02314 to 0.02295, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0537 - val_loss: 0.0230 - val_mse: 0.0230 - val_mae: 0.1225 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 468/500

Epoch 00468: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0526 - val_loss: 0.0230 - val_mse: 0.0230 - val_mae: 0.1227 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 469/500

Epoch 00469: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0527 - val_loss: 0.0232 - val_mse: 0.0232 - val_mae: 0.1234 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 470/500

Epoch 00470: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0522 - val_loss: 0.0234 - val_mse: 0.0234 - val_mae: 0.1241 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 471/500

Epoch 00471: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0529 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1243 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 472/500

Epoch 00472: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0554 - val_loss: 0.0234 - val_mse: 0.0234 - val_mae: 0.1241 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 473/500

Epoch 00473: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0552 - val_loss: 0.0234 - val_mse: 0.0234 - val_mae: 0.1242 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 474/500

Epoch 00474: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0527 - val_loss: 0.0234 - val_mse: 0.0234 - val_mae: 0.1240 - lr: 1.0000e-05 - 88ms/epoch - 5ms/step
Epoch 475/500

Epoch 00475: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0547 - val_loss: 0.0233 - val_mse: 0.0233 - val_mae: 0.1238 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 476/500

Epoch 00476: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0572 - val_loss: 0.0233 - val_mse: 0.0233 - val_mae: 0.1239 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 477/500

Epoch 00477: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0547 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1245 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 478/500

Epoch 00478: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0572 - val_loss: 0.0235 - val_mse: 0.0235 - val_mae: 0.1245 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 479/500

Epoch 00479: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0545 - val_loss: 0.0233 - val_mse: 0.0233 - val_mae: 0.1240 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 480/500

Epoch 00480: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0539 - val_loss: 0.0232 - val_mse: 0.0232 - val_mae: 0.1236 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 481/500

Epoch 00481: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0526 - val_loss: 0.0231 - val_mse: 0.0231 - val_mae: 0.1234 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 482/500

Epoch 00482: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0532 - val_loss: 0.0232 - val_mse: 0.0232 - val_mae: 0.1235 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 483/500

Epoch 00483: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0532 - val_loss: 0.0232 - val_mse: 0.0232 - val_mae: 0.1235 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 484/500

Epoch 00484: val_loss did not improve from 0.02295
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0551 - val_loss: 0.0230 - val_mse: 0.0230 - val_mae: 0.1229 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 485/500

Epoch 00485: val_loss improved from 0.02295 to 0.02291, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0539 - val_loss: 0.0229 - val_mse: 0.0229 - val_mae: 0.1228 - lr: 1.0000e-05 - 117ms/epoch - 7ms/step
Epoch 486/500

Epoch 00486: val_loss did not improve from 0.02291
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0543 - val_loss: 0.0230 - val_mse: 0.0230 - val_mae: 0.1231 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 487/500

Epoch 00487: val_loss improved from 0.02291 to 0.02280, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0045 - mse: 0.0045 - mae: 0.0526 - val_loss: 0.0228 - val_mse: 0.0228 - val_mae: 0.1224 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 488/500

Epoch 00488: val_loss improved from 0.02280 to 0.02264, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0555 - val_loss: 0.0226 - val_mse: 0.0226 - val_mae: 0.1219 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 489/500

Epoch 00489: val_loss improved from 0.02264 to 0.02257, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0540 - val_loss: 0.0226 - val_mse: 0.0226 - val_mae: 0.1217 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 490/500

Epoch 00490: val_loss did not improve from 0.02257
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0536 - val_loss: 0.0226 - val_mse: 0.0226 - val_mae: 0.1218 - lr: 1.0000e-05 - 88ms/epoch - 6ms/step
Epoch 491/500

Epoch 00491: val_loss did not improve from 0.02257
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0536 - val_loss: 0.0226 - val_mse: 0.0226 - val_mae: 0.1218 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 492/500

Epoch 00492: val_loss did not improve from 0.02257
16/16 - 0s - loss: 0.0039 - mse: 0.0039 - mae: 0.0493 - val_loss: 0.0226 - val_mse: 0.0226 - val_mae: 0.1220 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 493/500

Epoch 00493: val_loss did not improve from 0.02257
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0521 - val_loss: 0.0226 - val_mse: 0.0226 - val_mae: 0.1220 - lr: 1.0000e-05 - 79ms/epoch - 5ms/step
Epoch 494/500

Epoch 00494: val_loss improved from 0.02257 to 0.02240, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0526 - val_loss: 0.0224 - val_mse: 0.0224 - val_mae: 0.1212 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 495/500

Epoch 00495: val_loss improved from 0.02240 to 0.02230, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0542 - val_loss: 0.0223 - val_mse: 0.0223 - val_mae: 0.1209 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 496/500

Epoch 00496: val_loss improved from 0.02230 to 0.02204, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0546 - val_loss: 0.0220 - val_mse: 0.0220 - val_mae: 0.1201 - lr: 1.0000e-05 - 104ms/epoch - 7ms/step
Epoch 497/500

Epoch 00497: val_loss did not improve from 0.02204
16/16 - 0s - loss: 0.0049 - mse: 0.0049 - mae: 0.0551 - val_loss: 0.0221 - val_mse: 0.0221 - val_mae: 0.1202 - lr: 1.0000e-05 - 81ms/epoch - 5ms/step
Epoch 498/500

Epoch 00498: val_loss did not improve from 0.02204
16/16 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0532 - val_loss: 0.0221 - val_mse: 0.0221 - val_mae: 0.1203 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 499/500

Epoch 00499: val_loss improved from 0.02204 to 0.02197, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0548 - val_loss: 0.0220 - val_mse: 0.0220 - val_mae: 0.1199 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 500/500

Epoch 00500: val_loss improved from 0.02197 to 0.02183, saving model to LSTM7.h5
16/16 - 0s - loss: 0.0047 - mse: 0.0047 - mae: 0.0540 - val_loss: 0.0218 - val_mse: 0.0218 - val_mae: 0.1195 - lr: 1.0000e-05 - 117ms/epoch - 7ms/step

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 44.65212926265077 
RMSE:	 6.682224873696692 
MAPE:	 5.204686480071648

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 45.539825469272486 
RMSE:	 6.748320196113436 
MAPE:	 5.43245952292463
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.778, Time=3.53 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.587, Time=5.34 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-14597.576, Time=5.56 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.587, Time=8.44 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15338.693, Time=10.98 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15153.472, Time=25.66 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-17112.658, Time=15.33 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-14552.587, Time=10.00 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-15106.216, Time=14.12 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-12251.715, Time=35.41 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 134.382 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8588.329
Date:                Sun, 12 Dec 2021   AIC                         -17112.658
Time:                        18:30:04   BIC                         -16962.551
Sample:                             0   HQIC                        -17055.011
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1          -4.53e-09   3.26e-06     -0.001      0.999   -6.39e-06    6.38e-06
x2         -4.512e-09   3.25e-06     -0.001      0.999   -6.38e-06    6.37e-06
x3         -4.538e-09   3.26e-06     -0.001      0.999    -6.4e-06    6.39e-06
x4             1.0000   3.26e-06   3.07e+05      0.000       1.000       1.000
x5         -4.105e-09   3.11e-06     -0.001      0.999    -6.1e-06    6.09e-06
x6         -1.488e-08   5.45e-06     -0.003      0.998   -1.07e-05    1.07e-05
x7         -4.481e-09   3.24e-06     -0.001      0.999   -6.36e-06    6.36e-06
x8         -4.365e-09    3.2e-06     -0.001      0.999   -6.29e-06    6.28e-06
x9         -4.628e-10   8.38e-07     -0.001      1.000   -1.64e-06    1.64e-06
x10        -7.326e-10    1.3e-06     -0.001      1.000   -2.55e-06    2.54e-06
x11        -4.347e-09    3.2e-06     -0.001      0.999   -6.27e-06    6.26e-06
x12        -4.345e-09    3.2e-06     -0.001      0.999   -6.27e-06    6.26e-06
x13         -4.52e-09   3.26e-06     -0.001      0.999   -6.39e-06    6.38e-06
x14        -3.586e-08      9e-06     -0.004      0.997   -1.77e-05    1.76e-05
x15        -3.757e-09   2.98e-06     -0.001      0.999   -5.84e-06    5.83e-06
x16         -1.24e-08   5.36e-06     -0.002      0.998   -1.05e-05    1.05e-05
x17        -4.515e-09   3.26e-06     -0.001      0.999    -6.4e-06    6.39e-06
x18        -2.632e-10   7.07e-07     -0.000      1.000   -1.39e-06    1.39e-06
x19        -4.642e-09    3.3e-06     -0.001      0.999   -6.47e-06    6.46e-06
x20        -3.919e-10   6.91e-07     -0.001      1.000   -1.36e-06    1.35e-06
x21         -7.69e-09   4.13e-06     -0.002      0.999   -8.11e-06    8.09e-06
x22        -6.998e-12   2.69e-13    -25.970      0.000   -7.53e-12   -6.47e-12
x23         -1.81e-10   2.22e-12    -81.582      0.000   -1.85e-10   -1.77e-10
x24        -4.955e-08    8.9e-06     -0.006      0.996   -1.75e-05    1.74e-05
x25        -4.901e-08    8.4e-06     -0.006      0.995   -1.65e-05    1.64e-05
x26        -6.446e-08    1.2e-05     -0.005      0.996   -2.37e-05    2.35e-05
x27         -5.73e-08   1.14e-05     -0.005      0.996   -2.24e-05    2.23e-05
x28        -2.997e-08   8.22e-06     -0.004      0.997   -1.61e-05    1.61e-05
x29        -3.486e-08   8.89e-06     -0.004      0.997   -1.75e-05    1.74e-05
ma.L1         -1.3902   3.62e-10  -3.84e+09      0.000      -1.390      -1.390
ma.L2          0.4033   3.72e-10   1.08e+09      0.000       0.403       0.403
sigma2      8.541e-11   6.95e-11      1.229      0.219   -5.08e-11    2.22e-10
===================================================================================
Ljung-Box (L1) (Q):                  66.92   Jarque-Bera (JB):           6039240.46
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                            12.14
Prob(H) (two-sided):                  0.00   Kurtosis:                       426.63
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.94e+30. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.30534, saving model to LSTM7.h5
17/17 - 2s - loss: 0.1565 - mse: 0.1565 - mae: 0.3274 - val_loss: 0.3053 - val_mse: 0.3053 - val_mae: 0.5221 - lr: 0.0010 - 2s/epoch - 125ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.30534 to 0.25749, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0395 - mse: 0.0395 - mae: 0.1562 - val_loss: 0.2575 - val_mse: 0.2575 - val_mae: 0.4783 - lr: 0.0010 - 105ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.25749 to 0.23086, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0299 - mse: 0.0299 - mae: 0.1376 - val_loss: 0.2309 - val_mse: 0.2309 - val_mae: 0.4531 - lr: 0.0010 - 115ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.23086 to 0.22231, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0298 - mse: 0.0298 - mae: 0.1382 - val_loss: 0.2223 - val_mse: 0.2223 - val_mae: 0.4443 - lr: 0.0010 - 93ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.22231 to 0.19973, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0242 - mse: 0.0242 - mae: 0.1241 - val_loss: 0.1997 - val_mse: 0.1997 - val_mae: 0.4202 - lr: 0.0010 - 91ms/epoch - 5ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.19973 to 0.17981, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0206 - mse: 0.0206 - mae: 0.1142 - val_loss: 0.1798 - val_mse: 0.1798 - val_mae: 0.3972 - lr: 0.0010 - 118ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.17981 to 0.15455, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0186 - mse: 0.0186 - mae: 0.1092 - val_loss: 0.1545 - val_mse: 0.1545 - val_mae: 0.3666 - lr: 0.0010 - 97ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.15455
17/17 - 0s - loss: 0.0159 - mse: 0.0159 - mae: 0.1014 - val_loss: 0.1656 - val_mse: 0.1656 - val_mae: 0.3820 - lr: 0.0010 - 93ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.15455
17/17 - 0s - loss: 0.0138 - mse: 0.0138 - mae: 0.0929 - val_loss: 0.1584 - val_mse: 0.1584 - val_mae: 0.3740 - lr: 0.0010 - 84ms/epoch - 5ms/step
Epoch 10/500

Epoch 00010: val_loss improved from 0.15455 to 0.13938, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0111 - mse: 0.0111 - mae: 0.0830 - val_loss: 0.1394 - val_mse: 0.1394 - val_mae: 0.3495 - lr: 0.0010 - 120ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: val_loss improved from 0.13938 to 0.13594, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0119 - mse: 0.0119 - mae: 0.0867 - val_loss: 0.1359 - val_mse: 0.1359 - val_mae: 0.3454 - lr: 0.0010 - 101ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss improved from 0.13594 to 0.11705, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0112 - mse: 0.0112 - mae: 0.0822 - val_loss: 0.1171 - val_mse: 0.1171 - val_mae: 0.3192 - lr: 0.0010 - 112ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss improved from 0.11705 to 0.10633, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0095 - mse: 0.0095 - mae: 0.0773 - val_loss: 0.1063 - val_mse: 0.1063 - val_mae: 0.3032 - lr: 0.0010 - 109ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss improved from 0.10633 to 0.09558, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0089 - mse: 0.0089 - mae: 0.0741 - val_loss: 0.0956 - val_mse: 0.0956 - val_mae: 0.2868 - lr: 0.0010 - 118ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.09558
17/17 - 0s - loss: 0.0083 - mse: 0.0083 - mae: 0.0710 - val_loss: 0.1009 - val_mse: 0.1009 - val_mae: 0.2964 - lr: 0.0010 - 83ms/epoch - 5ms/step
Epoch 16/500

Epoch 00016: val_loss improved from 0.09558 to 0.08888, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0078 - mse: 0.0078 - mae: 0.0706 - val_loss: 0.0889 - val_mse: 0.0889 - val_mae: 0.2764 - lr: 0.0010 - 100ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss improved from 0.08888 to 0.08816, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0074 - mse: 0.0074 - mae: 0.0681 - val_loss: 0.0882 - val_mse: 0.0882 - val_mae: 0.2755 - lr: 0.0010 - 110ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.08816
17/17 - 0s - loss: 0.0072 - mse: 0.0072 - mae: 0.0655 - val_loss: 0.0902 - val_mse: 0.0902 - val_mae: 0.2802 - lr: 0.0010 - 77ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss improved from 0.08816 to 0.07791, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0067 - mse: 0.0067 - mae: 0.0647 - val_loss: 0.0779 - val_mse: 0.0779 - val_mae: 0.2589 - lr: 0.0010 - 118ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.07791
17/17 - 0s - loss: 0.0070 - mse: 0.0070 - mae: 0.0663 - val_loss: 0.0814 - val_mse: 0.0814 - val_mae: 0.2659 - lr: 0.0010 - 83ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.07791
17/17 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0607 - val_loss: 0.0787 - val_mse: 0.0787 - val_mae: 0.2605 - lr: 0.0010 - 81ms/epoch - 5ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.07791
17/17 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0586 - val_loss: 0.0842 - val_mse: 0.0842 - val_mae: 0.2709 - lr: 0.0010 - 90ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss improved from 0.07791 to 0.07391, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0059 - mse: 0.0059 - mae: 0.0603 - val_loss: 0.0739 - val_mse: 0.0739 - val_mae: 0.2531 - lr: 0.0010 - 104ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.07391
17/17 - 0s - loss: 0.0062 - mse: 0.0062 - mae: 0.0637 - val_loss: 0.0862 - val_mse: 0.0862 - val_mae: 0.2757 - lr: 0.0010 - 100ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.07391
17/17 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0578 - val_loss: 0.0755 - val_mse: 0.0755 - val_mae: 0.2557 - lr: 0.0010 - 99ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss improved from 0.07391 to 0.06662, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0046 - mse: 0.0046 - mae: 0.0541 - val_loss: 0.0666 - val_mse: 0.0666 - val_mae: 0.2391 - lr: 0.0010 - 102ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.06662
17/17 - 0s - loss: 0.0050 - mse: 0.0050 - mae: 0.0557 - val_loss: 0.0728 - val_mse: 0.0728 - val_mae: 0.2523 - lr: 0.0010 - 96ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss improved from 0.06662 to 0.06080, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0054 - mse: 0.0054 - mae: 0.0578 - val_loss: 0.0608 - val_mse: 0.0608 - val_mae: 0.2289 - lr: 0.0010 - 102ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.06080
17/17 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0564 - val_loss: 0.0626 - val_mse: 0.0626 - val_mae: 0.2327 - lr: 0.0010 - 80ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.06080
17/17 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0519 - val_loss: 0.0635 - val_mse: 0.0635 - val_mae: 0.2345 - lr: 0.0010 - 86ms/epoch - 5ms/step
Epoch 31/500

Epoch 00031: val_loss improved from 0.06080 to 0.04957, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0044 - mse: 0.0044 - mae: 0.0525 - val_loss: 0.0496 - val_mse: 0.0496 - val_mae: 0.2046 - lr: 0.0010 - 106ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04957
17/17 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0573 - val_loss: 0.0550 - val_mse: 0.0550 - val_mae: 0.2182 - lr: 0.0010 - 88ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss improved from 0.04957 to 0.04416, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0052 - mse: 0.0052 - mae: 0.0575 - val_loss: 0.0442 - val_mse: 0.0442 - val_mae: 0.1929 - lr: 0.0010 - 119ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04416
17/17 - 0s - loss: 0.0055 - mse: 0.0055 - mae: 0.0596 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2105 - lr: 0.0010 - 106ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04416
17/17 - 0s - loss: 0.0040 - mse: 0.0040 - mae: 0.0511 - val_loss: 0.0574 - val_mse: 0.0574 - val_mae: 0.2232 - lr: 0.0010 - 84ms/epoch - 5ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04416
17/17 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0564 - val_loss: 0.0517 - val_mse: 0.0517 - val_mae: 0.2116 - lr: 0.0010 - 85ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04416
17/17 - 0s - loss: 0.0053 - mse: 0.0053 - mae: 0.0576 - val_loss: 0.0497 - val_mse: 0.0497 - val_mae: 0.2078 - lr: 0.0010 - 89ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss improved from 0.04416 to 0.03520, saving model to LSTM7.h5
17/17 - 0s - loss: 0.0056 - mse: 0.0056 - mae: 0.0595 - val_loss: 0.0352 - val_mse: 0.0352 - val_mae: 0.1705 - lr: 0.0010 - 114ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0051 - mse: 0.0051 - mae: 0.0565 - val_loss: 0.0544 - val_mse: 0.0544 - val_mae: 0.2172 - lr: 0.0010 - 88ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0048 - mse: 0.0048 - mae: 0.0551 - val_loss: 0.0683 - val_mse: 0.0683 - val_mae: 0.2465 - lr: 0.0010 - 77ms/epoch - 5ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0063 - mse: 0.0063 - mae: 0.0637 - val_loss: 0.0464 - val_mse: 0.0464 - val_mae: 0.2005 - lr: 0.0010 - 84ms/epoch - 5ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0608 - val_loss: 0.0416 - val_mse: 0.0416 - val_mae: 0.1889 - lr: 0.0010 - 88ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00043: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0057 - mse: 0.0057 - mae: 0.0602 - val_loss: 0.0483 - val_mse: 0.0483 - val_mae: 0.2043 - lr: 0.0010 - 95ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0501 - val_loss: 0.0502 - val_mse: 0.0502 - val_mae: 0.2088 - lr: 1.0000e-04 - 87ms/epoch - 5ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0038 - mse: 0.0038 - mae: 0.0475 - val_loss: 0.0518 - val_mse: 0.0518 - val_mae: 0.2126 - lr: 1.0000e-04 - 80ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0473 - val_loss: 0.0516 - val_mse: 0.0516 - val_mae: 0.2120 - lr: 1.0000e-04 - 84ms/epoch - 5ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0467 - val_loss: 0.0504 - val_mse: 0.0504 - val_mae: 0.2096 - lr: 1.0000e-04 - 81ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00048: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0037 - mse: 0.0037 - mae: 0.0466 - val_loss: 0.0503 - val_mse: 0.0503 - val_mae: 0.2093 - lr: 1.0000e-04 - 97ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0033 - mse: 0.0033 - mae: 0.0444 - val_loss: 0.0503 - val_mse: 0.0503 - val_mae: 0.2092 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0032 - mse: 0.0032 - mae: 0.0445 - val_loss: 0.0503 - val_mse: 0.0503 - val_mae: 0.2092 - lr: 1.0000e-05 - 80ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0032 - mse: 0.0032 - mae: 0.0448 - val_loss: 0.0502 - val_mse: 0.0502 - val_mae: 0.2091 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0459 - val_loss: 0.0502 - val_mse: 0.0502 - val_mae: 0.2091 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 53/500

Epoch 00053: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00053: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0457 - val_loss: 0.0503 - val_mse: 0.0503 - val_mae: 0.2093 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0445 - val_loss: 0.0503 - val_mse: 0.0503 - val_mae: 0.2092 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0033 - mse: 0.0033 - mae: 0.0449 - val_loss: 0.0502 - val_mse: 0.0502 - val_mae: 0.2092 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0472 - val_loss: 0.0502 - val_mse: 0.0502 - val_mae: 0.2090 - lr: 1.0000e-05 - 87ms/epoch - 5ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0033 - mse: 0.0033 - mae: 0.0444 - val_loss: 0.0503 - val_mse: 0.0503 - val_mae: 0.2093 - lr: 1.0000e-05 - 89ms/epoch - 5ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0461 - val_loss: 0.0504 - val_mse: 0.0504 - val_mae: 0.2096 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0458 - val_loss: 0.0505 - val_mse: 0.0505 - val_mae: 0.2097 - lr: 1.0000e-05 - 108ms/epoch - 6ms/step
Epoch 60/500

Epoch 00060: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0449 - val_loss: 0.0505 - val_mse: 0.0505 - val_mae: 0.2099 - lr: 1.0000e-05 - 113ms/epoch - 7ms/step
Epoch 61/500

Epoch 00061: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0033 - mse: 0.0033 - mae: 0.0451 - val_loss: 0.0507 - val_mse: 0.0507 - val_mae: 0.2101 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 62/500

Epoch 00062: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0032 - mse: 0.0032 - mae: 0.0451 - val_loss: 0.0507 - val_mse: 0.0507 - val_mae: 0.2102 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 63/500

Epoch 00063: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0463 - val_loss: 0.0507 - val_mse: 0.0507 - val_mae: 0.2102 - lr: 1.0000e-05 - 86ms/epoch - 5ms/step
Epoch 64/500

Epoch 00064: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0463 - val_loss: 0.0507 - val_mse: 0.0507 - val_mae: 0.2102 - lr: 1.0000e-05 - 83ms/epoch - 5ms/step
Epoch 65/500

Epoch 00065: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0033 - mse: 0.0033 - mae: 0.0448 - val_loss: 0.0506 - val_mse: 0.0506 - val_mae: 0.2101 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 66/500

Epoch 00066: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0469 - val_loss: 0.0505 - val_mse: 0.0505 - val_mae: 0.2099 - lr: 1.0000e-05 - 93ms/epoch - 5ms/step
Epoch 67/500

Epoch 00067: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0448 - val_loss: 0.0506 - val_mse: 0.0506 - val_mae: 0.2100 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 68/500

Epoch 00068: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0467 - val_loss: 0.0507 - val_mse: 0.0507 - val_mae: 0.2102 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 69/500

Epoch 00069: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0466 - val_loss: 0.0505 - val_mse: 0.0505 - val_mae: 0.2098 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 70/500

Epoch 00070: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0453 - val_loss: 0.0505 - val_mse: 0.0505 - val_mae: 0.2098 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 71/500

Epoch 00071: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0445 - val_loss: 0.0506 - val_mse: 0.0506 - val_mae: 0.2100 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 72/500

Epoch 00072: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0462 - val_loss: 0.0506 - val_mse: 0.0506 - val_mae: 0.2100 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 73/500

Epoch 00073: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0033 - mse: 0.0033 - mae: 0.0443 - val_loss: 0.0505 - val_mse: 0.0505 - val_mae: 0.2098 - lr: 1.0000e-05 - 93ms/epoch - 5ms/step
Epoch 74/500

Epoch 00074: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0467 - val_loss: 0.0506 - val_mse: 0.0506 - val_mae: 0.2101 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 75/500

Epoch 00075: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0466 - val_loss: 0.0506 - val_mse: 0.0506 - val_mae: 0.2100 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 76/500

Epoch 00076: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0458 - val_loss: 0.0505 - val_mse: 0.0505 - val_mae: 0.2098 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 77/500

Epoch 00077: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0033 - mse: 0.0033 - mae: 0.0452 - val_loss: 0.0504 - val_mse: 0.0504 - val_mae: 0.2097 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 78/500

Epoch 00078: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0465 - val_loss: 0.0504 - val_mse: 0.0504 - val_mae: 0.2096 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 79/500

Epoch 00079: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0459 - val_loss: 0.0504 - val_mse: 0.0504 - val_mae: 0.2096 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 80/500

Epoch 00080: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0449 - val_loss: 0.0504 - val_mse: 0.0504 - val_mae: 0.2097 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 81/500

Epoch 00081: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0464 - val_loss: 0.0506 - val_mse: 0.0506 - val_mae: 0.2100 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 82/500

Epoch 00082: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0465 - val_loss: 0.0505 - val_mse: 0.0505 - val_mae: 0.2097 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 83/500

Epoch 00083: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0034 - mse: 0.0034 - mae: 0.0464 - val_loss: 0.0506 - val_mse: 0.0506 - val_mae: 0.2100 - lr: 1.0000e-05 - 84ms/epoch - 5ms/step
Epoch 84/500

Epoch 00084: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0031 - mse: 0.0031 - mae: 0.0431 - val_loss: 0.0506 - val_mse: 0.0506 - val_mae: 0.2102 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 85/500

Epoch 00085: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0033 - mse: 0.0033 - mae: 0.0443 - val_loss: 0.0506 - val_mse: 0.0506 - val_mae: 0.2100 - lr: 1.0000e-05 - 93ms/epoch - 5ms/step
Epoch 86/500

Epoch 00086: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0035 - mse: 0.0035 - mae: 0.0463 - val_loss: 0.0505 - val_mse: 0.0505 - val_mae: 0.2099 - lr: 1.0000e-05 - 82ms/epoch - 5ms/step
Epoch 87/500

Epoch 00087: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0036 - mse: 0.0036 - mae: 0.0464 - val_loss: 0.0505 - val_mse: 0.0505 - val_mae: 0.2099 - lr: 1.0000e-05 - 91ms/epoch - 5ms/step
Epoch 88/500

Epoch 00088: val_loss did not improve from 0.03520
17/17 - 0s - loss: 0.0033 - mse: 0.0033 - mae: 0.0452 - val_loss: 0.0505 - val_mse: 0.0505 - val_mae: 0.2100 - lr: 1.0000e-05 - 85ms/epoch - 5ms/step
Epoch 00088: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 44.65212926265077 
RMSE:	 6.682224873696692 
MAPE:	 5.204686480071648

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 45.539825469272486 
RMSE:	 6.748320196113436 
MAPE:	 5.43245952292463

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 42.30488040231578 
RMSE:	 6.504220199402522 
MAPE:	 5.010195929360332
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.776, Time=3.29 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.586, Time=5.34 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16271.755, Time=7.16 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.586, Time=8.20 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15152.908, Time=10.90 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-14481.105, Time=12.97 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16088.109, Time=20.81 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17014.021, Time=6.25 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-16988.615, Time=3.78 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17071.454, Time=7.55 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=inf, Time=18.60 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-16987.981, Time=4.57 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-16982.666, Time=4.55 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 114.014 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8569.727
Date:                Sun, 12 Dec 2021   AIC                         -17071.454
Time:                        18:36:11   BIC                         -16911.965
Sample:                             0   HQIC                        -17010.203
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1           -2.8e-10   6.02e-05  -4.65e-06      1.000      -0.000       0.000
x2         -2.817e-10   6.04e-05  -4.66e-06      1.000      -0.000       0.000
x3         -2.805e-10   6.03e-05  -4.65e-06      1.000      -0.000       0.000
x4             1.0000   6.03e-05   1.66e+04      0.000       1.000       1.000
x5           -2.6e-10    5.8e-05  -4.48e-06      1.000      -0.000       0.000
x6         -1.389e-09      0.000  -1.08e-05      1.000      -0.000       0.000
x7         -2.789e-10   6.01e-05  -4.64e-06      1.000      -0.000       0.000
x8         -2.763e-10   5.99e-05  -4.62e-06      1.000      -0.000       0.000
x9         -2.224e-12    1.6e-06  -1.39e-06      1.000   -3.13e-06    3.13e-06
x10        -1.345e-10   4.12e-05  -3.26e-06      1.000   -8.08e-05    8.08e-05
x11          -2.9e-10   6.12e-05  -4.74e-06      1.000      -0.000       0.000
x12        -2.602e-10   5.82e-05  -4.47e-06      1.000      -0.000       0.000
x13        -2.807e-10   6.03e-05  -4.65e-06      1.000      -0.000       0.000
x14         -1.87e-09      0.000   -1.2e-05      1.000      -0.000       0.000
x15        -2.844e-10   6.05e-05   -4.7e-06      1.000      -0.000       0.000
x16        -7.962e-11    3.2e-05  -2.48e-06      1.000   -6.28e-05    6.28e-05
x17        -2.445e-10   5.61e-05  -4.36e-06      1.000      -0.000       0.000
x18          -6.4e-10   9.15e-05  -6.99e-06      1.000      -0.000       0.000
x19        -2.923e-10   6.14e-05  -4.76e-06      1.000      -0.000       0.000
x20        -4.336e-10   7.41e-05  -5.86e-06      1.000      -0.000       0.000
x21         -4.55e-10    7.5e-05  -6.07e-06      1.000      -0.000       0.000
x22        -3.587e-13   1.42e-11     -0.025      0.980   -2.82e-11    2.75e-11
x23        -1.088e-11   9.56e-11     -0.114      0.909   -1.98e-10    1.76e-10
x24        -2.146e-09      0.000  -1.63e-05      1.000      -0.000       0.000
x25        -1.637e-09      0.000  -1.35e-05      1.000      -0.000       0.000
x26        -3.147e-09      0.000  -1.56e-05      1.000      -0.000       0.000
x27         -2.58e-09      0.000  -1.41e-05      1.000      -0.000       0.000
x28        -2.444e-09      0.000  -1.37e-05      1.000      -0.000       0.000
x29        -1.666e-09      0.000  -1.13e-05      1.000      -0.000       0.000
ar.L1         -0.4923    5.1e-10  -9.65e+08      0.000      -0.492      -0.492
ar.L2         -0.1923   2.96e-10  -6.49e+08      0.000      -0.192      -0.192
ar.L3         -0.0462    1.4e-10  -3.29e+08      0.000      -0.046      -0.046
ma.L1         -0.7077   1.16e-09  -6.12e+08      0.000      -0.708      -0.708
sigma2       8.99e-11   6.96e-11      1.291      0.197   -4.66e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  54.06   Jarque-Bera (JB):           4126495.58
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.48
Prob(H) (two-sided):                  0.00   Kurtosis:                       353.58
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 2.01e+30. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.85386, saving model to LSTM7.h5
10/10 - 2s - loss: 0.7346 - mse: 0.7346 - mae: 0.7356 - val_loss: 0.8539 - val_mse: 0.8539 - val_mae: 0.9053 - lr: 0.0010 - 2s/epoch - 218ms/step
Epoch 2/500

Epoch 00002: val_loss improved from 0.85386 to 0.57893, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0770 - mse: 0.0770 - mae: 0.2318 - val_loss: 0.5789 - val_mse: 0.5789 - val_mae: 0.7425 - lr: 0.0010 - 75ms/epoch - 8ms/step
Epoch 3/500

Epoch 00003: val_loss improved from 0.57893 to 0.40598, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0758 - mse: 0.0758 - mae: 0.2373 - val_loss: 0.4060 - val_mse: 0.4060 - val_mae: 0.6181 - lr: 0.0010 - 92ms/epoch - 9ms/step
Epoch 4/500

Epoch 00004: val_loss improved from 0.40598 to 0.29908, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0418 - mse: 0.0418 - mae: 0.1718 - val_loss: 0.2991 - val_mse: 0.2991 - val_mae: 0.5267 - lr: 0.0010 - 95ms/epoch - 9ms/step
Epoch 5/500

Epoch 00005: val_loss improved from 0.29908 to 0.23737, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0252 - mse: 0.0252 - mae: 0.1260 - val_loss: 0.2374 - val_mse: 0.2374 - val_mae: 0.4658 - lr: 0.0010 - 72ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: val_loss improved from 0.23737 to 0.20982, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0257 - mse: 0.0257 - mae: 0.1275 - val_loss: 0.2098 - val_mse: 0.2098 - val_mae: 0.4361 - lr: 0.0010 - 117ms/epoch - 12ms/step
Epoch 7/500

Epoch 00007: val_loss improved from 0.20982 to 0.18859, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0218 - mse: 0.0218 - mae: 0.1176 - val_loss: 0.1886 - val_mse: 0.1886 - val_mae: 0.4119 - lr: 0.0010 - 92ms/epoch - 9ms/step
Epoch 8/500

Epoch 00008: val_loss improved from 0.18859 to 0.17341, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0192 - mse: 0.0192 - mae: 0.1121 - val_loss: 0.1734 - val_mse: 0.1734 - val_mae: 0.3936 - lr: 0.0010 - 101ms/epoch - 10ms/step
Epoch 9/500

Epoch 00009: val_loss improved from 0.17341 to 0.16995, saving model to LSTM7.h5
10/10 - 0s - loss: 0.0199 - mse: 0.0199 - mae: 0.1131 - val_loss: 0.1699 - val_mse: 0.1699 - val_mae: 0.3894 - lr: 0.0010 - 97ms/epoch - 10ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0174 - mse: 0.0174 - mae: 0.1035 - val_loss: 0.1730 - val_mse: 0.1730 - val_mae: 0.3934 - lr: 0.0010 - 60ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0164 - mse: 0.0164 - mae: 0.1036 - val_loss: 0.1854 - val_mse: 0.1854 - val_mae: 0.4085 - lr: 0.0010 - 68ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0156 - mse: 0.0156 - mae: 0.0984 - val_loss: 0.1808 - val_mse: 0.1808 - val_mae: 0.4030 - lr: 0.0010 - 73ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0136 - mse: 0.0136 - mae: 0.0937 - val_loss: 0.1780 - val_mse: 0.1780 - val_mae: 0.3994 - lr: 0.0010 - 72ms/epoch - 7ms/step
Epoch 14/500

Epoch 00014: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00014: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0146 - mse: 0.0146 - mae: 0.0952 - val_loss: 0.1813 - val_mse: 0.1813 - val_mae: 0.4035 - lr: 0.0010 - 67ms/epoch - 7ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0141 - mse: 0.0141 - mae: 0.0942 - val_loss: 0.1807 - val_mse: 0.1807 - val_mae: 0.4028 - lr: 1.0000e-04 - 77ms/epoch - 8ms/step
Epoch 16/500

Epoch 00016: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0143 - mse: 0.0143 - mae: 0.0947 - val_loss: 0.1810 - val_mse: 0.1810 - val_mae: 0.4031 - lr: 1.0000e-04 - 76ms/epoch - 8ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0129 - mse: 0.0129 - mae: 0.0924 - val_loss: 0.1803 - val_mse: 0.1803 - val_mae: 0.4024 - lr: 1.0000e-04 - 83ms/epoch - 8ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0126 - mse: 0.0126 - mae: 0.0895 - val_loss: 0.1790 - val_mse: 0.1790 - val_mae: 0.4007 - lr: 1.0000e-04 - 86ms/epoch - 9ms/step
Epoch 19/500

Epoch 00019: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00019: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0131 - mse: 0.0131 - mae: 0.0911 - val_loss: 0.1779 - val_mse: 0.1779 - val_mae: 0.3994 - lr: 1.0000e-04 - 63ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0133 - mse: 0.0133 - mae: 0.0925 - val_loss: 0.1777 - val_mse: 0.1777 - val_mae: 0.3991 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0127 - mse: 0.0127 - mae: 0.0892 - val_loss: 0.1774 - val_mse: 0.1774 - val_mae: 0.3988 - lr: 1.0000e-05 - 60ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0135 - mse: 0.0135 - mae: 0.0925 - val_loss: 0.1773 - val_mse: 0.1773 - val_mae: 0.3986 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0142 - mse: 0.0142 - mae: 0.0963 - val_loss: 0.1770 - val_mse: 0.1770 - val_mae: 0.3983 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 24/500

Epoch 00024: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00024: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0127 - mse: 0.0127 - mae: 0.0896 - val_loss: 0.1768 - val_mse: 0.1768 - val_mae: 0.3980 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0123 - mse: 0.0123 - mae: 0.0889 - val_loss: 0.1767 - val_mse: 0.1767 - val_mae: 0.3979 - lr: 1.0000e-05 - 77ms/epoch - 8ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0122 - mse: 0.0122 - mae: 0.0880 - val_loss: 0.1766 - val_mse: 0.1766 - val_mae: 0.3978 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0116 - mse: 0.0116 - mae: 0.0855 - val_loss: 0.1765 - val_mse: 0.1765 - val_mae: 0.3977 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0130 - mse: 0.0130 - mae: 0.0897 - val_loss: 0.1763 - val_mse: 0.1763 - val_mae: 0.3974 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0121 - mse: 0.0121 - mae: 0.0880 - val_loss: 0.1762 - val_mse: 0.1762 - val_mae: 0.3972 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0129 - mse: 0.0129 - mae: 0.0908 - val_loss: 0.1760 - val_mse: 0.1760 - val_mae: 0.3970 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0129 - mse: 0.0129 - mae: 0.0895 - val_loss: 0.1758 - val_mse: 0.1758 - val_mae: 0.3968 - lr: 1.0000e-05 - 58ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0127 - mse: 0.0127 - mae: 0.0891 - val_loss: 0.1756 - val_mse: 0.1756 - val_mae: 0.3966 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0132 - mse: 0.0132 - mae: 0.0908 - val_loss: 0.1755 - val_mse: 0.1755 - val_mae: 0.3965 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0137 - mse: 0.0137 - mae: 0.0942 - val_loss: 0.1754 - val_mse: 0.1754 - val_mae: 0.3963 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0130 - mse: 0.0130 - mae: 0.0905 - val_loss: 0.1753 - val_mse: 0.1753 - val_mae: 0.3962 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0125 - mse: 0.0125 - mae: 0.0882 - val_loss: 0.1753 - val_mse: 0.1753 - val_mae: 0.3961 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0122 - mse: 0.0122 - mae: 0.0883 - val_loss: 0.1751 - val_mse: 0.1751 - val_mae: 0.3959 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0124 - mse: 0.0124 - mae: 0.0875 - val_loss: 0.1749 - val_mse: 0.1749 - val_mae: 0.3957 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0137 - mse: 0.0137 - mae: 0.0911 - val_loss: 0.1747 - val_mse: 0.1747 - val_mae: 0.3954 - lr: 1.0000e-05 - 83ms/epoch - 8ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0133 - mse: 0.0133 - mae: 0.0913 - val_loss: 0.1744 - val_mse: 0.1744 - val_mae: 0.3951 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0124 - mse: 0.0124 - mae: 0.0887 - val_loss: 0.1742 - val_mse: 0.1742 - val_mae: 0.3949 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0117 - mse: 0.0117 - mae: 0.0859 - val_loss: 0.1742 - val_mse: 0.1742 - val_mae: 0.3948 - lr: 1.0000e-05 - 82ms/epoch - 8ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0137 - mse: 0.0137 - mae: 0.0927 - val_loss: 0.1742 - val_mse: 0.1742 - val_mae: 0.3949 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0136 - mse: 0.0136 - mae: 0.0925 - val_loss: 0.1742 - val_mse: 0.1742 - val_mae: 0.3948 - lr: 1.0000e-05 - 92ms/epoch - 9ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0135 - mse: 0.0135 - mae: 0.0925 - val_loss: 0.1742 - val_mse: 0.1742 - val_mae: 0.3948 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0127 - mse: 0.0127 - mae: 0.0897 - val_loss: 0.1740 - val_mse: 0.1740 - val_mae: 0.3946 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0143 - mse: 0.0143 - mae: 0.0941 - val_loss: 0.1740 - val_mse: 0.1740 - val_mae: 0.3945 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0129 - mse: 0.0129 - mae: 0.0911 - val_loss: 0.1740 - val_mse: 0.1740 - val_mae: 0.3946 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0126 - mse: 0.0126 - mae: 0.0901 - val_loss: 0.1740 - val_mse: 0.1740 - val_mae: 0.3946 - lr: 1.0000e-05 - 63ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0124 - mse: 0.0124 - mae: 0.0886 - val_loss: 0.1741 - val_mse: 0.1741 - val_mae: 0.3947 - lr: 1.0000e-05 - 57ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0128 - mse: 0.0128 - mae: 0.0892 - val_loss: 0.1739 - val_mse: 0.1739 - val_mae: 0.3944 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 52/500

Epoch 00052: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0130 - mse: 0.0130 - mae: 0.0903 - val_loss: 0.1734 - val_mse: 0.1734 - val_mae: 0.3939 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 53/500

Epoch 00053: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0127 - mse: 0.0127 - mae: 0.0905 - val_loss: 0.1731 - val_mse: 0.1731 - val_mae: 0.3934 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 54/500

Epoch 00054: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0127 - mse: 0.0127 - mae: 0.0888 - val_loss: 0.1727 - val_mse: 0.1727 - val_mae: 0.3930 - lr: 1.0000e-05 - 85ms/epoch - 9ms/step
Epoch 55/500

Epoch 00055: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0131 - mse: 0.0131 - mae: 0.0902 - val_loss: 0.1728 - val_mse: 0.1728 - val_mae: 0.3930 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 56/500

Epoch 00056: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0137 - mse: 0.0137 - mae: 0.0907 - val_loss: 0.1727 - val_mse: 0.1727 - val_mae: 0.3930 - lr: 1.0000e-05 - 62ms/epoch - 6ms/step
Epoch 57/500

Epoch 00057: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0131 - mse: 0.0131 - mae: 0.0901 - val_loss: 0.1725 - val_mse: 0.1725 - val_mae: 0.3927 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 58/500

Epoch 00058: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0130 - mse: 0.0130 - mae: 0.0907 - val_loss: 0.1726 - val_mse: 0.1726 - val_mae: 0.3928 - lr: 1.0000e-05 - 61ms/epoch - 6ms/step
Epoch 59/500

Epoch 00059: val_loss did not improve from 0.16995
10/10 - 0s - loss: 0.0132 - mse: 0.0132 - mae: 0.0906 - val_loss: 0.1724 - val_mse: 0.1724 - val_mae: 0.3926 - lr: 1.0000e-05 - 56ms/epoch - 6ms/step
Epoch 00059: early stopping

SMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 44.65212926265077 
RMSE:	 6.682224873696692 
MAPE:	 5.204686480071648

EMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	49.25% Accuracy
MSE:	 45.539825469272486 
RMSE:	 6.748320196113436 
MAPE:	 5.43245952292463

WMA
Prediction vs Close:		52.99% Accuracy
Prediction vs Prediction:	50.0% Accuracy
MSE:	 42.30488040231578 
RMSE:	 6.504220199402522 
MAPE:	 5.010195929360332

DEMA
Prediction vs Close:		55.6% Accuracy
Prediction vs Prediction:	54.48% Accuracy
MSE:	 23.305922116020078 
RMSE:	 4.827620751055335 
MAPE:	 3.7452201197397774
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.104, Time=3.79 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.591, Time=5.51 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16779.655, Time=11.07 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.590, Time=8.68 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16989.430, Time=4.19 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-16990.286, Time=3.92 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-16988.543, Time=4.21 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-16987.154, Time=4.39 sec
 ARIMA(2,3,0)(0,0,0)[0] intercept   : AIC=-16533.935, Time=16.56 sec

Best model:  ARIMA(2,3,0)(0,0,0)[0]          
Total fit time: 62.346 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(2, 3, 0)   Log Likelihood                8527.143
Date:                Sun, 12 Dec 2021   AIC                         -16990.286
Time:                        18:46:16   BIC                         -16840.179
Sample:                             0   HQIC                        -16932.639
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1           -1.1e-16        nan        nan        nan         nan         nan
x2         -3.811e-16         -0        inf      0.000   -3.81e-16   -3.81e-16
x3          8.776e-16   4.38e-27      2e+11      0.000    8.78e-16    8.78e-16
x4             1.0000   4.36e-27   2.29e+26      0.000       1.000       1.000
x5          6.686e-16   4.14e-27   1.61e+11      0.000    6.69e-16    6.69e-16
x6         -5.238e-17   9.44e-27  -5.55e+09      0.000   -5.24e-17   -5.24e-17
x7         -1.709e-16   4.37e-27  -3.91e+10      0.000   -1.71e-16   -1.71e-16
x8          1.439e-15   4.33e-27   3.32e+11      0.000    1.44e-15    1.44e-15
x9         -2.924e-16   5.73e-28   -5.1e+11      0.000   -2.92e-16   -2.92e-16
x10        -1.028e-16   1.78e-27  -5.76e+10      0.000   -1.03e-16   -1.03e-16
x11        -4.338e-16   4.31e-27  -1.01e+11      0.000   -4.34e-16   -4.34e-16
x12          1.72e-16   4.33e-27   3.97e+10      0.000    1.72e-16    1.72e-16
x13        -3.011e-16   4.36e-27  -6.91e+10      0.000   -3.01e-16   -3.01e-16
x14        -2.611e-16   1.27e-26  -2.06e+10      0.000   -2.61e-16   -2.61e-16
x15          1.53e-14   4.46e-27   3.43e+12      0.000    1.53e-14    1.53e-14
x16        -1.401e-14   5.45e-27  -2.57e+12      0.000    -1.4e-14    -1.4e-14
x17         2.316e-14   4.12e-27   5.62e+12      0.000    2.32e-14    2.32e-14
x18        -3.727e-15   3.71e-27  -1.01e+12      0.000   -3.73e-15   -3.73e-15
x19        -1.361e-14   4.94e-27  -2.75e+12      0.000   -1.36e-14   -1.36e-14
x20        -5.277e-15   6.08e-27  -8.68e+11      0.000   -5.28e-15   -5.28e-15
x21         1.178e-18   3.12e-27   3.77e+08      0.000    1.18e-18    1.18e-18
x22        -8.779e-17   1.74e-29  -5.05e+12      0.000   -8.78e-17   -8.78e-17
x23         3.183e-17   5.91e-29   5.39e+11      0.000    3.18e-17    3.18e-17
x24        -1.683e-16   1.41e-26  -1.19e+10      0.000   -1.68e-16   -1.68e-16
x25         8.988e-17   1.48e-30   6.08e+13      0.000    8.99e-17    8.99e-17
x26         4.435e-17   1.58e-26    2.8e+09      0.000    4.44e-17    4.44e-17
x27         1.538e-16   8.87e-27   1.73e+10      0.000    1.54e-16    1.54e-16
x28         1.635e-16   1.22e-26   1.34e+10      0.000    1.63e-16    1.63e-16
x29         1.474e-16   6.34e-27   2.33e+10      0.000    1.47e-16    1.47e-16
ar.L1         -0.9879   1.21e-22  -8.16e+21      0.000      -0.988      -0.988
ar.L2         -0.4879   1.29e-22  -3.79e+21      0.000      -0.488      -0.488
sigma2          1e-10   6.99e-11      1.432      0.152   -3.69e-11    2.37e-10
===================================================================================
Ljung-Box (L1) (Q):                  57.29   Jarque-Bera (JB):            559955.86
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.13   Skew:                             0.64
Prob(H) (two-sided):                  0.00   Kurtosis:                       132.20
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number    inf. Standard errors may be unstable.

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/mlemodel.py:2968: RuntimeWarning: divide by zero encountered in true_divide
  return self.params / self.bse

Architecture Used¶

from google.colab import files
import cv2
uploaded = files.upload()

Saving Experiment7.png to Experiment7 (1).png

img = cv2.imread('Experiment7.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)

<matplotlib.image.AxesImage at 0x7fa65007efd0>

Model Plots¶

for i in range(len(list(simulation7.keys()))):
  SIM = list(simulation7.keys())[i]
  plot_train(simulation7,SIM)
  plot_test(simulation7,SIM)

----- Train RMSE for SMA ----- 9.009338337956548
----- Train_MSE_LSTM for SMA ----- 81.16817728777366
----- Train MAE LSTM for SMA ----- 7.791349936760778

----- Test RMSE for SMA----- 6.682224873696692
----- Test_MSE_LSTM for SMA----- 44.65212926265077
----- Test_MAE_LSTM for SMA----- 5.204686480071648

----- Train RMSE for EMA ----- 10.75589930055345
----- Train_MSE_LSTM for EMA ----- 115.68936976364621
----- Train MAE LSTM for EMA ----- 9.582493831136144

----- Test RMSE for EMA----- 6.748320196113436
----- Test_MSE_LSTM for EMA----- 45.539825469272486
----- Test_MAE_LSTM for EMA----- 5.43245952292463

----- Train RMSE for WMA ----- 10.908509232790552
----- Train_MSE_LSTM for WMA ----- 118.9955736818767
----- Train MAE LSTM for WMA ----- 9.800814582394565

----- Test RMSE for WMA----- 6.504220199402522
----- Test_MSE_LSTM for WMA----- 42.30488040231578
----- Test_MAE_LSTM for WMA----- 5.010195929360332

----- Train RMSE for DEMA ----- 12.643440847440496
----- Train_MSE_LSTM for DEMA ----- 159.85659646272686
----- Train MAE LSTM for DEMA ----- 11.36962745253845

----- Test RMSE for DEMA----- 4.827620751055335
----- Test_MSE_LSTM for DEMA----- 23.305922116020078
----- Test_MAE_LSTM for DEMA----- 3.7452201197397774

----- Train RMSE for KAMA ----- 11.147835109393704
----- Train_MSE_LSTM for KAMA ----- 124.27422762623091
----- Train MAE LSTM for KAMA ----- 10.178621601225753

----- Test RMSE for KAMA----- 4.252333670621163
----- Test_MSE_LSTM for KAMA----- 18.082341646298453
----- Test_MAE_LSTM for KAMA----- 3.4333194517527637

Arima w Exogenous Variable Multistep MutiVariate LSTM Hybrid Model Experiment 8¶

def get_arima_exog(dataframe,original_data, train_len, test_len):    
    

    # prepare train and test data for exogenous vr
    X_value = pd.DataFrame(low_vol.iloc[:, :])
    y_value = pd.DataFrame(low_vol.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    X_scale_dataset = X_scaler.fit_transform(X_value)
    y_scale_dataset = y_scaler.fit_transform(y_value)
    # Get data and check shape
    # X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X_scale_dataset)
    y_train, y_test, = split_train_test(y_scale_dataset)
    yc_train,yc_test = split_train_test(low_vol_data)
    yc = yc_test.values.tolist()
    y_train_list = y_train.flatten().tolist()
    y_test_list = y_test.flatten().tolist()
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)

    # Initialize model
    model = auto_arima(y_train_list,exogenous  = X_train,trace=True, error_action='ignore', start_p=1,start_q=1,max_p=3,max_q=3,d=3,
            suppress_warnings=True,stepwise=True,seasonal=True)

      # Determine model parameters
    print(model.summary())
    model.fit(y_train_list,maxiter=200)
    order = model.get_params()['order']
    print('ARIMA order:', order, '\n')

      # Genereate predictions
    prediction = []
    for i in range(len(y_test_list)):
        model = pmdarima.ARIMA(order=order)
        model.fit(y_train_list)
        # print('working on', i+1, 'of', len(y_test), '-- ' + str(int(100 * (i + 1) / len(y_test))) + '% complete')

        prediction.append(model.predict()[0])
        y_train_list.append(y_test_list[i])

    predictionte = y_scaler.inverse_transform(np.array(prediction).reshape(-1,1))
    y_test_ = y_scaler.inverse_transform(np.array(y_test_list).reshape(-1,1))

    # Generate error data
    mse = mean_squared_error(yc_test, predictionte)
    rmse = mse ** 0.5
    mae = mean_absolute_error(y_test_ , predictionte )
    return yc,predictionte.flatten().tolist(), mse, rmse, mae

def get_lstm(data,original_data, train_len, test_len,img_file,ma ,lstm_len=3):
    # prepare train and test data
    X_value = pd.DataFrame(data.iloc[:, :])
    y_value = pd.DataFrame(data.iloc[:, 3])
    X_scaler = MinMaxScaler(feature_range=(-1, 1))
    y_scaler = MinMaxScaler(feature_range=(-1, 1))
    X_scaler.fit(X_value)
    y_scaler.fit(y_value)
    # Get data and check shape
    X, y, yc = get_X_y(X_scale_dataset, y_scale_dataset)#X will be of shape 224 X 3 X 21 (each 3 X 21 array will be 3 days' worth of data). yc will have the corresponding closing price value
    # pdb.set_trace()
    X_train, X_test, = split_train_test(X)
    y_train, y_test, = split_train_test(y)
    # yc_train, yc_test, = split_train_test(original_data)
    index_train, index_test, = predict_index(dataset_final, X_train, n_steps_in, n_steps_out)
    det =20
    input_dim = X_train.shape[1]#3
    feature_size = X_train.shape[2]#24
    output_dim = y_train.shape[1]#1



    # Option 1
    # Set up & fit LSTM RNN
    # model = Sequential()
    # model.add(LSTM(256, activation='relu', kernel_initializer='he_normal', input_shape=(input_dim, feature_size)))
    # model.add(Dense(units=64,activation='relu'))
    # model.add(Dropout(0.5))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(learning_rate = 0.001), loss='mse')

    # ## Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM1.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma_' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()


    # # # option 2
    # model = Sequential()
    # model.add(Bidirectional(LSTM(units= 128), input_shape=(input_dim, feature_size)))
    # model.add(Dense(64))
    # model.add(Dense(units=output_dim))
    # model.compile(optimizer=Adam(lr = 0.001), loss='mean_squared_error', metrics=['accuracy'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM7.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma+' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # Option 3
    # define custom activation
    # reference: https://github.com/Vaibhav-Sachdeva/Correlation-Coefficient-Prediction-using-ARIMA-LSTM-Hybrid-Model/blob/main/Code/LSTM-ARIMA.ipynb
    # class Double_Tanh(Activation):
    #     def __init__(self, activation, **kwargs):
    #         super(Double_Tanh, self).__init__(activation, **kwargs)
    #         self.__name__ = 'double_tanh'

    # def double_tanh(x):
    #     return (K.tanh(x) * 2)

    # get_custom_objects().update({'double_tanh':Double_Tanh(double_tanh)})
    #     # Model Generation
    # model = Sequential()
    # #check https://machinelearningmastery.com/use-weight-regularization-lstm-networks-time-series-forecasting/
    # model.add(LSTM(25, input_shape=(input_dim, feature_size), dropout=0.2, kernel_regularizer=l1_l2(0.00,0.00), bias_regularizer=l1_l2(0.00,0.00)))
    # model.add(Dense(1))
    # model.add(Activation(double_tanh))
    # model.compile(loss='mean_squared_error', optimizer='adam', metrics=['mse', 'mae'])
    # # Common code
    # callbacks = [
    # EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    # ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    # ModelCheckpoint('LSTM7.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    # fname1 = img_file+'.png'
    # tensorflow.keras.utils.plot_model(
    #     model, to_file=fname1, show_shapes=True, show_dtype=False,
    #     show_layer_names=True, expand_nested=False, dpi=96,
    #     layer_range=None, show_layer_activations=False
    # )
    # history = model.fit(X_train, y_train, epochs=500, batch_size=1, verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # # plot loss
    # fname2 = img_file+'-'+ma
    # plt.title(img_file+'-'+ma+' Loss')
    # plt.xlabel("Epochs")
    # plt.ylabel("Loss")
    # pyplot.plot(history.history['loss'], label='train')
    # pyplot.plot(history.history['val_loss'], label='validation')
    # pyplot.legend()
    # pyplot.savefig(fname2+'.png',dpi='figure')
    # pyplot.show()

    # #Option 4
    # # Set up & fit LSTM RNN
    model = Sequential()
    model.add(LSTM(units=lstm_len, return_sequences=True, input_shape=(input_dim, feature_size)))
    model.add(LSTM(units=int(lstm_len/2)))
    model.add(Dense(1, activation='sigmoid'))
    model.compile(loss='mean_squared_error', optimizer='adam')
    # Common code
    callbacks = [
    EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=50),
    ReduceLROnPlateau(factor=0.1, patience=5, min_lr=0.00001, verbose=1),
    ModelCheckpoint('LSTM8.h5', verbose=1, save_best_only=True, save_weights_only=True)]
    fname1 = img_file+'.png'
    tensorflow.keras.utils.plot_model(
        model, to_file=fname1, show_shapes=True, show_dtype=False,
        show_layer_names=True, expand_nested=False, dpi=96,
        layer_range=None, show_layer_activations=False
    )
    history = model.fit(X_train, y_train, epochs=500, batch_size=int( optimized_period[ma]), verbose=2, callbacks=callbacks, validation_data=(X_test, y_test),shuffle=False)
    # plot loss
    fname2 = img_file+'-'+ma
    plt.title(img_file+'-'+ma+' Loss')
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    pyplot.plot(history.history['loss'], label='train')
    pyplot.plot(history.history['val_loss'], label='validation')
    pyplot.legend()
    pyplot.savefig(fname2+'.png',dpi='figure')
    pyplot.show()



    # Generate predictions
    predictiontr = model.predict(X_train, verbose=0)
    predictiontr = y_scaler.inverse_transform(predictiontr).tolist()
    outputtr = []
    for i in range(len(predictiontr)):
        outputtr.extend(predictiontr[i])
    predictiontr = outputtr
    # Generate error data

    ## replace with yc , xtest generated by new multistep method
    mse_tr = mean_squared_error(y_train, predictiontr)
    rmse_tr = mse_tr ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictiontr))
    mae_tr = mean_absolute_error(y_train, pd.Series(predictiontr))
    # Original_tr = pd.Series(yc_train)
    Original_tr = y_scaler.inverse_transform(y_train).flatten().tolist()


    predictionte = model.predict(X_test, verbose=0)
    predictionte = (y_scaler.inverse_transform(predictionte)-det).tolist()
    outputte = []
    for i in range(len(predictionte)):
        outputte.extend(predictionte[i])
    predictionte = outputte
    # Generate error data

    mse_te = mean_squared_error(y_test, predictionte)
    rmse_te = mse_te ** 0.5
    # mape = mean_absolute_percentage_error(X_test, pd.Series(predictionte))
    mae_te = mean_absolute_error(y_test, pd.Series(predictionte))
    # Original_te = pd.Series(yc_test)
    Original_te = y_scaler.inverse_transform(y_test).flatten().tolist()

    return Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,Original_te,predictionte, mse_te,rmse_te,mae_te

if __name__ == '__main__':
    start_time = timeit.default_timer()
    simulation8 = {}
    imgfile = 'Experiment8'
    for ma in optimized_period:
                print(ma)
                print(functions[ma])
                print ( int( optimized_period[ma]))
              # if ma == 'SMA':
                low_vol = df.apply(lambda c:  functions[ma](c, timeperiod = int( optimized_period[ma])))
                low_vol = low_vol.fillna(0)
                low_vol_data = df['close']
                high_vol = pd.DataFrame()
                df2 = df.copy()
                for i in df2.columns:
                  if i in low_vol.columns:
                    high_vol[i] = df2[i].subtract(low_vol[i], fill_value=0)
                high_vol_data = df['close']
                ## *****************************************************
                # Generate ARIMA and LSTM predictions
                print('\nWorking on ' + ma + ' predictions')
                try:
                  print('parameters used : ', train_len, test_len)
                  low_vol_Original, low_vol_prediction, low_vol_mse, low_vol_rmse,low_vol_mae = get_arima_exog(low_vol,low_vol_data, train_len, test_len)
                except:
                    print('ARIMA error, skipping to next MA type')
                    continue
                Original_tr, predictiontr, mse_tr, rmse_tr,mae_tr,high_vol_Original, high_vol_prediction, high_vol_mse, high_vol_rmse,high_vol_mae, = get_lstm(high_vol,high_vol_data, train_len, test_len,imgfile,ma)
                final_prediction_tr = df['close'].head(train_len).values + pd.Series(predictiontr) # ignoring first 3 steps 
                mse_ftr = mean_squared_error(df['close'].head(train_len).values,final_prediction_tr.values)
                rmse_ftr = mse_ftr ** 0.5
                mape_ftr = mean_absolute_percentage_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)
                mae_ftr = mean_absolute_error(df['close'].head(train_len).reset_index(drop=True), final_prediction_tr)

                final_prediction = pd.Series(low_vol_prediction[3:]) + pd.Series(high_vol_prediction)
                mse = mean_squared_error(df['close'].tail(test_len).values,final_prediction.values)
                rmse = mse ** 0.5
                mape = mean_absolute_percentage_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                mae = mean_absolute_error(df['close'].tail(test_len).reset_index(drop=True), final_prediction)
                # Generate prediction accuracy
                actual = df['close'].tail(test_len).values
                result_1 = []
                result_2 = []
                for i in range(1, len(final_prediction)):
                    # Compare prediction to previous close price
                    if final_prediction[i] > actual[i-1] and actual[i] > actual[i-1]:
                        result_1.append(1)
                    elif final_prediction[i] < actual[i-1] and actual[i] < actual[i-1]:
                        result_1.append(1)
                    else:
                        result_1.append(0)

                    # Compare prediction to previous prediction
                    if final_prediction[i] > final_prediction[i-1] and actual[i] > actual[i-1]:
                        result_2.append(1)
                    elif final_prediction[i] < final_prediction[i-1] and actual[i] < actual[i-1]:
                        result_2.append(1)
                    else:
                        result_2.append(0)

                accuracy_1 = np.mean(result_1)
                accuracy_2 = np.mean(result_2)

                simulation8[ma] = {'low_vol': {'original':list(low_vol_Original), 'prediction': list(low_vol_prediction) , 'mse': low_vol_mse,
                                              'rmse': low_vol_rmse, 'mae' : low_vol_mae},
                                  'high_vol': {'original':list(high_vol_Original),'prediction': list(high_vol_prediction), 'mse': high_vol_mse,
                                              'rmse': high_vol_rmse, 'mae' : high_vol_mae},
                                  'final_tr': {'original':df['close'].head(train_len).tolist(),'prediction': final_prediction_tr.values.tolist(), 'mse': mse_ftr,
                                              'rmse': rmse_ftr, 'mae' : mae_ftr},
                                  'final': {'original': df['close'].tail(test_len).tolist(), 'prediction': final_prediction.values.tolist(), 'mse': mse,
                                            'rmse': rmse, 'mae': mae },
                                  'accuracy': {'prediction vs close': accuracy_1, 'prediction vs prediction': accuracy_2}}

                # save simulation data here as checkpoint
                with open('simulation8_data.json', 'w') as fp:
                    json.dump(simulation8, fp)

                for ma in simulation8.keys():
                    print('\n' + ma)
                    print('Prediction vs Close:\t\t' + str(round(100*simulation8[ma]['accuracy']['prediction vs close'], 2))
                          + '% Accuracy')
                    print('Prediction vs Prediction:\t' + str(round(100*simulation8[ma]['accuracy']['prediction vs prediction'], 2))
                          + '% Accuracy')
                    print('MSE:\t', simulation8[ma]['final']['mse'],
                          '\nRMSE:\t', simulation8[ma]['final']['rmse'],
                          '\nMAPE:\t', simulation8[ma]['final']['mae'])#,
                          # '\nMAPE:\t', simulation[ma]['final']['mape'])
              # else:
              #   break
    elapsed = timeit.default_timer() - start_time
    print('Runtime: mins:',elapsed/60)

SMA
SMA([input_arrays], [timeperiod=30])

Simple Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
17

Working on SMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.787, Time=3.71 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.588, Time=5.64 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-14596.280, Time=5.73 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.588, Time=8.68 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16924.805, Time=10.33 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-14482.349, Time=11.41 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-17215.608, Time=21.10 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-14552.588, Time=10.18 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-15570.350, Time=18.92 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-11671.292, Time=28.02 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 123.736 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8639.804
Date:                Sun, 12 Dec 2021   AIC                         -17215.608
Time:                        19:15:57   BIC                         -17065.501
Sample:                             0   HQIC                        -17157.961
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -4.057e-09   5.82e-05  -6.97e-05      1.000      -0.000       0.000
x2         -4.057e-09   5.81e-05  -6.99e-05      1.000      -0.000       0.000
x3         -4.111e-09   5.49e-05  -7.49e-05      1.000      -0.000       0.000
x4             1.0000   5.71e-05   1.75e+04      0.000       1.000       1.000
x5         -3.706e-09   5.43e-05  -6.82e-05      1.000      -0.000       0.000
x6         -1.082e-08      0.000  -6.08e-05      1.000      -0.000       0.000
x7         -4.025e-09   5.63e-05  -7.15e-05      1.000      -0.000       0.000
x8         -4.035e-09   5.19e-05  -7.78e-05      1.000      -0.000       0.000
x9         -1.522e-10    2.9e-05  -5.25e-06      1.000   -5.68e-05    5.68e-05
x10        -6.396e-10   1.04e-05  -6.15e-05      1.000   -2.04e-05    2.04e-05
x11        -3.921e-09   5.06e-05  -7.75e-05      1.000   -9.91e-05    9.91e-05
x12        -4.102e-09   5.29e-05  -7.76e-05      1.000      -0.000       0.000
x13        -4.087e-09   5.75e-05  -7.11e-05      1.000      -0.000       0.000
x14        -3.619e-08      0.000     -0.000      1.000      -0.000       0.000
x15        -4.806e-09   4.61e-05     -0.000      1.000   -9.03e-05    9.03e-05
x16        -3.507e-09      0.000  -2.98e-05      1.000      -0.000       0.000
x17        -3.121e-09   6.02e-05  -5.18e-05      1.000      -0.000       0.000
x18        -1.172e-08      0.000     -0.000      1.000      -0.000       0.000
x19        -5.433e-09   6.06e-05  -8.96e-05      1.000      -0.000       0.000
x20        -1.393e-08   4.79e-05     -0.000      1.000   -9.39e-05    9.39e-05
x21        -4.216e-09   6.63e-05  -6.36e-05      1.000      -0.000       0.000
x22        -3.479e-11   1.66e-08     -0.002      0.998   -3.25e-08    3.24e-08
x23        -9.221e-10    1.4e-07     -0.007      0.995   -2.74e-07    2.73e-07
x24        -8.085e-08      0.001  -6.96e-05      1.000      -0.002       0.002
x25        -9.642e-08      0.001     -0.000      1.000      -0.002       0.002
x26        -5.019e-08      0.000     -0.000      1.000      -0.000       0.000
x27        -2.457e-08   7.65e-05     -0.000      1.000      -0.000       0.000
x28        -3.411e-08      0.000     -0.000      1.000      -0.000       0.000
x29        -1.507e-08   4.36e-05     -0.000      1.000   -8.54e-05    8.54e-05
ma.L1         -1.3898   8.03e-07  -1.73e+06      0.000      -1.390      -1.390
ma.L2          0.4031   8.36e-07   4.82e+05      0.000       0.403       0.403
sigma2      7.528e-11   7.24e-11      1.040      0.298   -6.66e-11    2.17e-10
===================================================================================
Ljung-Box (L1) (Q):                  89.12   Jarque-Bera (JB):           1533103.33
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.01   Skew:                             5.56
Prob(H) (two-sided):                  0.00   Kurtosis:                       216.50
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.08e+25. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04793, saving model to LSTM8.h5
48/48 - 3s - loss: 1.4063 - val_loss: 0.0479 - lr: 0.0010 - 3s/epoch - 71ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04793
48/48 - 0s - loss: 1.1570 - val_loss: 0.0499 - lr: 0.0010 - 233ms/epoch - 5ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.9394 - val_loss: 0.0520 - lr: 0.0010 - 273ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.8556 - val_loss: 0.0541 - lr: 0.0010 - 243ms/epoch - 5ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.8087 - val_loss: 0.0562 - lr: 0.0010 - 267ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7767 - val_loss: 0.0583 - lr: 0.0010 - 262ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7614 - val_loss: 0.0585 - lr: 1.0000e-04 - 258ms/epoch - 5ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7592 - val_loss: 0.0588 - lr: 1.0000e-04 - 234ms/epoch - 5ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7571 - val_loss: 0.0590 - lr: 1.0000e-04 - 266ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7549 - val_loss: 0.0592 - lr: 1.0000e-04 - 277ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7528 - val_loss: 0.0595 - lr: 1.0000e-04 - 258ms/epoch - 5ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7514 - val_loss: 0.0595 - lr: 1.0000e-05 - 270ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7512 - val_loss: 0.0595 - lr: 1.0000e-05 - 287ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7510 - val_loss: 0.0596 - lr: 1.0000e-05 - 257ms/epoch - 5ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7508 - val_loss: 0.0596 - lr: 1.0000e-05 - 268ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7505 - val_loss: 0.0596 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7503 - val_loss: 0.0597 - lr: 1.0000e-05 - 243ms/epoch - 5ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7501 - val_loss: 0.0597 - lr: 1.0000e-05 - 242ms/epoch - 5ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7498 - val_loss: 0.0597 - lr: 1.0000e-05 - 255ms/epoch - 5ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7496 - val_loss: 0.0597 - lr: 1.0000e-05 - 255ms/epoch - 5ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7494 - val_loss: 0.0598 - lr: 1.0000e-05 - 264ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7491 - val_loss: 0.0598 - lr: 1.0000e-05 - 252ms/epoch - 5ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7489 - val_loss: 0.0598 - lr: 1.0000e-05 - 259ms/epoch - 5ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7486 - val_loss: 0.0599 - lr: 1.0000e-05 - 277ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7484 - val_loss: 0.0599 - lr: 1.0000e-05 - 258ms/epoch - 5ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7481 - val_loss: 0.0599 - lr: 1.0000e-05 - 267ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7479 - val_loss: 0.0600 - lr: 1.0000e-05 - 253ms/epoch - 5ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7477 - val_loss: 0.0600 - lr: 1.0000e-05 - 245ms/epoch - 5ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7474 - val_loss: 0.0600 - lr: 1.0000e-05 - 259ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7472 - val_loss: 0.0601 - lr: 1.0000e-05 - 269ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7469 - val_loss: 0.0601 - lr: 1.0000e-05 - 233ms/epoch - 5ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7466 - val_loss: 0.0601 - lr: 1.0000e-05 - 234ms/epoch - 5ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7464 - val_loss: 0.0602 - lr: 1.0000e-05 - 271ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7461 - val_loss: 0.0602 - lr: 1.0000e-05 - 266ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7459 - val_loss: 0.0602 - lr: 1.0000e-05 - 272ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7456 - val_loss: 0.0603 - lr: 1.0000e-05 - 255ms/epoch - 5ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7454 - val_loss: 0.0603 - lr: 1.0000e-05 - 256ms/epoch - 5ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7451 - val_loss: 0.0604 - lr: 1.0000e-05 - 288ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7449 - val_loss: 0.0604 - lr: 1.0000e-05 - 258ms/epoch - 5ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7446 - val_loss: 0.0604 - lr: 1.0000e-05 - 265ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7443 - val_loss: 0.0605 - lr: 1.0000e-05 - 323ms/epoch - 7ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7441 - val_loss: 0.0605 - lr: 1.0000e-05 - 252ms/epoch - 5ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7438 - val_loss: 0.0605 - lr: 1.0000e-05 - 245ms/epoch - 5ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7436 - val_loss: 0.0606 - lr: 1.0000e-05 - 273ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7433 - val_loss: 0.0606 - lr: 1.0000e-05 - 238ms/epoch - 5ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7431 - val_loss: 0.0607 - lr: 1.0000e-05 - 274ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7428 - val_loss: 0.0607 - lr: 1.0000e-05 - 262ms/epoch - 5ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7425 - val_loss: 0.0607 - lr: 1.0000e-05 - 296ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7423 - val_loss: 0.0608 - lr: 1.0000e-05 - 278ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7420 - val_loss: 0.0608 - lr: 1.0000e-05 - 242ms/epoch - 5ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04793
48/48 - 0s - loss: 0.7418 - val_loss: 0.0609 - lr: 1.0000e-05 - 246ms/epoch - 5ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	49.63% Accuracy
MSE:	 30.79397335917816 
RMSE:	 5.549231780992587 
MAPE:	 4.345848876898189
EMA
EMA([input_arrays], [timeperiod=30])

Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
51

Working on EMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.778, Time=3.50 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.587, Time=5.43 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-15952.568, Time=15.01 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.587, Time=7.85 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16628.634, Time=10.96 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-16462.206, Time=24.67 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16848.298, Time=13.03 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17014.023, Time=6.75 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-16988.619, Time=3.61 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17071.454, Time=7.63 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=inf, Time=18.64 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-16987.994, Time=3.95 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-16982.667, Time=4.79 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 125.840 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8569.727
Date:                Sun, 12 Dec 2021   AIC                         -17071.454
Time:                        19:21:56   BIC                         -16911.966
Sample:                             0   HQIC                        -17010.204
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1         -2.316e-10   6.25e-05  -3.71e-06      1.000      -0.000       0.000
x2         -2.309e-10   6.24e-05   -3.7e-06      1.000      -0.000       0.000
x3         -2.325e-10   6.26e-05  -3.71e-06      1.000      -0.000       0.000
x4             1.0000   6.25e-05    1.6e+04      0.000       1.000       1.000
x5         -2.107e-10   5.96e-05  -3.54e-06      1.000      -0.000       0.000
x6         -7.997e-10      0.000  -7.41e-06      1.000      -0.000       0.000
x7         -2.295e-10   6.22e-05  -3.69e-06      1.000      -0.000       0.000
x8         -2.246e-10   6.15e-05  -3.65e-06      1.000      -0.000       0.000
x9         -1.167e-11   1.25e-05  -9.33e-07      1.000   -2.45e-05    2.45e-05
x10        -4.454e-11   2.66e-05  -1.68e-06      1.000   -5.21e-05    5.21e-05
x11        -2.221e-10   6.11e-05  -3.63e-06      1.000      -0.000       0.000
x12        -2.266e-10   6.18e-05  -3.66e-06      1.000      -0.000       0.000
x13        -2.315e-10   6.25e-05  -3.71e-06      1.000      -0.000       0.000
x14        -1.767e-09      0.000  -1.02e-05      1.000      -0.000       0.000
x15         -2.11e-10   5.93e-05  -3.56e-06      1.000      -0.000       0.000
x16        -5.283e-10   9.45e-05  -5.59e-06      1.000      -0.000       0.000
x17        -2.098e-10   6.01e-05  -3.49e-06      1.000      -0.000       0.000
x18         -3.82e-11   2.41e-05  -1.58e-06      1.000   -4.73e-05    4.73e-05
x19        -2.645e-10   6.61e-05     -4e-06      1.000      -0.000       0.000
x20        -2.417e-10   6.21e-05  -3.89e-06      1.000      -0.000       0.000
x21        -4.824e-10   8.83e-05  -5.46e-06      1.000      -0.000       0.000
x22        -3.758e-13   1.19e-11     -0.032      0.975   -2.36e-11    2.29e-11
x23        -1.089e-11   8.42e-11     -0.129      0.897   -1.76e-10    1.54e-10
x24        -2.538e-09      0.000  -1.44e-05      1.000      -0.000       0.000
x25        -2.038e-09      0.000  -1.49e-05      1.000      -0.000       0.000
x26         -3.16e-09      0.000  -1.37e-05      1.000      -0.000       0.000
x27        -2.955e-09      0.000  -1.32e-05      1.000      -0.000       0.000
x28        -1.664e-09      0.000  -9.94e-06      1.000      -0.000       0.000
x29        -1.568e-09      0.000  -9.63e-06      1.000      -0.000       0.000
ar.L1         -0.4923    6.2e-10  -7.94e+08      0.000      -0.492      -0.492
ar.L2         -0.1923    3.6e-10  -5.35e+08      0.000      -0.192      -0.192
ar.L3         -0.0462   1.71e-10  -2.71e+08      0.000      -0.046      -0.046
ma.L1         -0.7077   1.41e-09  -5.04e+08      0.000      -0.708      -0.708
sigma2       8.99e-11   6.96e-11      1.291      0.197   -4.66e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  51.79   Jarque-Bera (JB):           4012066.18
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.44
Prob(H) (two-sided):                  0.00   Kurtosis:                       348.68
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 5.01e+30. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.05184, saving model to LSTM8.h5
16/16 - 3s - loss: 1.4618 - val_loss: 0.0518 - lr: 0.0010 - 3s/epoch - 214ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.3997 - val_loss: 0.0525 - lr: 0.0010 - 120ms/epoch - 8ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.3470 - val_loss: 0.0533 - lr: 0.0010 - 107ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.3012 - val_loss: 0.0541 - lr: 0.0010 - 99ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.2618 - val_loss: 0.0549 - lr: 0.0010 - 99ms/epoch - 6ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.2275 - val_loss: 0.0558 - lr: 0.0010 - 85ms/epoch - 5ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.2070 - val_loss: 0.0559 - lr: 1.0000e-04 - 95ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.2040 - val_loss: 0.0560 - lr: 1.0000e-04 - 94ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.2011 - val_loss: 0.0562 - lr: 1.0000e-04 - 96ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1982 - val_loss: 0.0563 - lr: 1.0000e-04 - 93ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1954 - val_loss: 0.0564 - lr: 1.0000e-04 - 95ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1936 - val_loss: 0.0564 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1933 - val_loss: 0.0564 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1930 - val_loss: 0.0564 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1927 - val_loss: 0.0564 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1924 - val_loss: 0.0564 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1921 - val_loss: 0.0564 - lr: 1.0000e-05 - 93ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1919 - val_loss: 0.0565 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1916 - val_loss: 0.0565 - lr: 1.0000e-05 - 108ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1913 - val_loss: 0.0565 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1910 - val_loss: 0.0565 - lr: 1.0000e-05 - 109ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1907 - val_loss: 0.0565 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1904 - val_loss: 0.0565 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1901 - val_loss: 0.0565 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1899 - val_loss: 0.0565 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1896 - val_loss: 0.0565 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1893 - val_loss: 0.0566 - lr: 1.0000e-05 - 119ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1890 - val_loss: 0.0566 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1887 - val_loss: 0.0566 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1884 - val_loss: 0.0566 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1881 - val_loss: 0.0566 - lr: 1.0000e-05 - 118ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1878 - val_loss: 0.0566 - lr: 1.0000e-05 - 124ms/epoch - 8ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1876 - val_loss: 0.0566 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1873 - val_loss: 0.0566 - lr: 1.0000e-05 - 105ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1870 - val_loss: 0.0566 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1867 - val_loss: 0.0567 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1864 - val_loss: 0.0567 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1861 - val_loss: 0.0567 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1858 - val_loss: 0.0567 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1855 - val_loss: 0.0567 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1853 - val_loss: 0.0567 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1850 - val_loss: 0.0567 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1847 - val_loss: 0.0567 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1844 - val_loss: 0.0568 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1841 - val_loss: 0.0568 - lr: 1.0000e-05 - 116ms/epoch - 7ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1838 - val_loss: 0.0568 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1835 - val_loss: 0.0568 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1832 - val_loss: 0.0568 - lr: 1.0000e-05 - 91ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1830 - val_loss: 0.0568 - lr: 1.0000e-05 - 90ms/epoch - 6ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1827 - val_loss: 0.0568 - lr: 1.0000e-05 - 92ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.05184
16/16 - 0s - loss: 1.1824 - val_loss: 0.0568 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	49.63% Accuracy
MSE:	 30.79397335917816 
RMSE:	 5.549231780992587 
MAPE:	 4.345848876898189

EMA
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 32.37277762407691 
RMSE:	 5.689708043834667 
MAPE:	 4.4297291061987245
WMA
WMA([input_arrays], [timeperiod=30])

Weighted Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
49

Working on WMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.778, Time=3.35 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.587, Time=5.41 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-14597.576, Time=5.52 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.587, Time=7.97 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15338.693, Time=10.63 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-15153.472, Time=26.39 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-17112.658, Time=15.13 sec
 ARIMA(0,3,3)(0,0,0)[0]             : AIC=-14552.587, Time=10.63 sec
 ARIMA(1,3,3)(0,0,0)[0]             : AIC=-15106.216, Time=13.83 sec
 ARIMA(0,3,2)(0,0,0)[0] intercept   : AIC=-12251.715, Time=34.06 sec

Best model:  ARIMA(0,3,2)(0,0,0)[0]          
Total fit time: 132.942 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(0, 3, 2)   Log Likelihood                8588.329
Date:                Sun, 12 Dec 2021   AIC                         -17112.658
Time:                        19:32:50   BIC                         -16962.551
Sample:                             0   HQIC                        -17055.011
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1          -4.53e-09   3.26e-06     -0.001      0.999   -6.39e-06    6.38e-06
x2         -4.512e-09   3.25e-06     -0.001      0.999   -6.38e-06    6.37e-06
x3         -4.538e-09   3.26e-06     -0.001      0.999    -6.4e-06    6.39e-06
x4             1.0000   3.26e-06   3.07e+05      0.000       1.000       1.000
x5         -4.105e-09   3.11e-06     -0.001      0.999    -6.1e-06    6.09e-06
x6         -1.488e-08   5.45e-06     -0.003      0.998   -1.07e-05    1.07e-05
x7         -4.481e-09   3.24e-06     -0.001      0.999   -6.36e-06    6.36e-06
x8         -4.365e-09    3.2e-06     -0.001      0.999   -6.29e-06    6.28e-06
x9         -4.628e-10   8.38e-07     -0.001      1.000   -1.64e-06    1.64e-06
x10        -7.326e-10    1.3e-06     -0.001      1.000   -2.55e-06    2.54e-06
x11        -4.347e-09    3.2e-06     -0.001      0.999   -6.27e-06    6.26e-06
x12        -4.345e-09    3.2e-06     -0.001      0.999   -6.27e-06    6.26e-06
x13         -4.52e-09   3.26e-06     -0.001      0.999   -6.39e-06    6.38e-06
x14        -3.586e-08      9e-06     -0.004      0.997   -1.77e-05    1.76e-05
x15        -3.757e-09   2.98e-06     -0.001      0.999   -5.84e-06    5.83e-06
x16         -1.24e-08   5.36e-06     -0.002      0.998   -1.05e-05    1.05e-05
x17        -4.515e-09   3.26e-06     -0.001      0.999    -6.4e-06    6.39e-06
x18        -2.632e-10   7.07e-07     -0.000      1.000   -1.39e-06    1.39e-06
x19        -4.642e-09    3.3e-06     -0.001      0.999   -6.47e-06    6.46e-06
x20        -3.919e-10   6.91e-07     -0.001      1.000   -1.36e-06    1.35e-06
x21         -7.69e-09   4.13e-06     -0.002      0.999   -8.11e-06    8.09e-06
x22        -6.998e-12   2.69e-13    -25.970      0.000   -7.53e-12   -6.47e-12
x23         -1.81e-10   2.22e-12    -81.582      0.000   -1.85e-10   -1.77e-10
x24        -4.955e-08    8.9e-06     -0.006      0.996   -1.75e-05    1.74e-05
x25        -4.901e-08    8.4e-06     -0.006      0.995   -1.65e-05    1.64e-05
x26        -6.446e-08    1.2e-05     -0.005      0.996   -2.37e-05    2.35e-05
x27         -5.73e-08   1.14e-05     -0.005      0.996   -2.24e-05    2.23e-05
x28        -2.997e-08   8.22e-06     -0.004      0.997   -1.61e-05    1.61e-05
x29        -3.486e-08   8.89e-06     -0.004      0.997   -1.75e-05    1.74e-05
ma.L1         -1.3902   3.62e-10  -3.84e+09      0.000      -1.390      -1.390
ma.L2          0.4033   3.72e-10   1.08e+09      0.000       0.403       0.403
sigma2      8.541e-11   6.95e-11      1.229      0.219   -5.08e-11    2.22e-10
===================================================================================
Ljung-Box (L1) (Q):                  66.92   Jarque-Bera (JB):           6039240.46
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                            12.14
Prob(H) (two-sided):                  0.00   Kurtosis:                       426.63
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 4.94e+30. Standard errors may be unstable.
ARIMA order: (0, 3, 2) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04179, saving model to LSTM8.h5
17/17 - 4s - loss: 1.3396 - val_loss: 0.0418 - lr: 0.0010 - 4s/epoch - 219ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.2689 - val_loss: 0.0421 - lr: 0.0010 - 101ms/epoch - 6ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.2104 - val_loss: 0.0427 - lr: 0.0010 - 104ms/epoch - 6ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.1615 - val_loss: 0.0435 - lr: 0.0010 - 101ms/epoch - 6ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.1191 - val_loss: 0.0444 - lr: 0.0010 - 120ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0813 - val_loss: 0.0454 - lr: 0.0010 - 115ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0585 - val_loss: 0.0455 - lr: 1.0000e-04 - 99ms/epoch - 6ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0552 - val_loss: 0.0456 - lr: 1.0000e-04 - 110ms/epoch - 6ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0519 - val_loss: 0.0458 - lr: 1.0000e-04 - 96ms/epoch - 6ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0488 - val_loss: 0.0459 - lr: 1.0000e-04 - 105ms/epoch - 6ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0456 - val_loss: 0.0460 - lr: 1.0000e-04 - 96ms/epoch - 6ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0436 - val_loss: 0.0460 - lr: 1.0000e-05 - 90ms/epoch - 5ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0432 - val_loss: 0.0460 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0429 - val_loss: 0.0460 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0426 - val_loss: 0.0460 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0423 - val_loss: 0.0461 - lr: 1.0000e-05 - 97ms/epoch - 6ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0420 - val_loss: 0.0461 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0417 - val_loss: 0.0461 - lr: 1.0000e-05 - 109ms/epoch - 6ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0414 - val_loss: 0.0461 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0410 - val_loss: 0.0461 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0407 - val_loss: 0.0461 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0404 - val_loss: 0.0461 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0401 - val_loss: 0.0462 - lr: 1.0000e-05 - 149ms/epoch - 9ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0398 - val_loss: 0.0462 - lr: 1.0000e-05 - 119ms/epoch - 7ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0395 - val_loss: 0.0462 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0391 - val_loss: 0.0462 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0388 - val_loss: 0.0462 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0385 - val_loss: 0.0462 - lr: 1.0000e-05 - 96ms/epoch - 6ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0382 - val_loss: 0.0462 - lr: 1.0000e-05 - 90ms/epoch - 5ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0379 - val_loss: 0.0463 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0376 - val_loss: 0.0463 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0372 - val_loss: 0.0463 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0369 - val_loss: 0.0463 - lr: 1.0000e-05 - 100ms/epoch - 6ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0366 - val_loss: 0.0463 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0363 - val_loss: 0.0463 - lr: 1.0000e-05 - 101ms/epoch - 6ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0360 - val_loss: 0.0464 - lr: 1.0000e-05 - 107ms/epoch - 6ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0357 - val_loss: 0.0464 - lr: 1.0000e-05 - 106ms/epoch - 6ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0353 - val_loss: 0.0464 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0350 - val_loss: 0.0464 - lr: 1.0000e-05 - 94ms/epoch - 6ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0347 - val_loss: 0.0464 - lr: 1.0000e-05 - 95ms/epoch - 6ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0344 - val_loss: 0.0464 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0341 - val_loss: 0.0465 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0337 - val_loss: 0.0465 - lr: 1.0000e-05 - 105ms/epoch - 6ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0334 - val_loss: 0.0465 - lr: 1.0000e-05 - 112ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0331 - val_loss: 0.0465 - lr: 1.0000e-05 - 98ms/epoch - 6ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0328 - val_loss: 0.0465 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0325 - val_loss: 0.0465 - lr: 1.0000e-05 - 103ms/epoch - 6ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0322 - val_loss: 0.0466 - lr: 1.0000e-05 - 102ms/epoch - 6ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0318 - val_loss: 0.0466 - lr: 1.0000e-05 - 89ms/epoch - 5ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0315 - val_loss: 0.0466 - lr: 1.0000e-05 - 99ms/epoch - 6ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04179
17/17 - 0s - loss: 1.0312 - val_loss: 0.0466 - lr: 1.0000e-05 - 104ms/epoch - 6ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	49.63% Accuracy
MSE:	 30.79397335917816 
RMSE:	 5.549231780992587 
MAPE:	 4.345848876898189

EMA
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 32.37277762407691 
RMSE:	 5.689708043834667 
MAPE:	 4.4297291061987245

WMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 58.067607397948805 
RMSE:	 7.620210456276704 
MAPE:	 6.244282675104111
DEMA
DEMA([input_arrays], [timeperiod=30])

Double Exponential Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
89

Working on DEMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.776, Time=3.39 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.586, Time=5.37 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16271.755, Time=7.19 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.586, Time=8.20 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-15152.908, Time=10.72 sec
 ARIMA(1,3,2)(0,0,0)[0]             : AIC=-14481.105, Time=13.34 sec
 ARIMA(0,3,2)(0,0,0)[0]             : AIC=-16088.109, Time=21.31 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-17014.021, Time=7.29 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-16988.615, Time=3.39 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-17071.454, Time=7.26 sec
 ARIMA(3,3,2)(0,0,0)[0]             : AIC=inf, Time=17.72 sec

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/sarimax.py:1906: RuntimeWarning: divide by zero encountered in reciprocal
  return np.roots(self.polynomial_reduced_ma)**-1

 ARIMA(2,3,2)(0,0,0)[0]             : AIC=-16987.981, Time=4.26 sec
 ARIMA(3,3,1)(0,0,0)[0] intercept   : AIC=-16982.666, Time=4.59 sec

Best model:  ARIMA(3,3,1)(0,0,0)[0]          
Total fit time: 114.053 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(3, 3, 1)   Log Likelihood                8569.727
Date:                Sun, 12 Dec 2021   AIC                         -17071.454
Time:                        19:39:03   BIC                         -16911.965
Sample:                             0   HQIC                        -17010.203
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1           -2.8e-10   6.02e-05  -4.65e-06      1.000      -0.000       0.000
x2         -2.817e-10   6.04e-05  -4.66e-06      1.000      -0.000       0.000
x3         -2.805e-10   6.03e-05  -4.65e-06      1.000      -0.000       0.000
x4             1.0000   6.03e-05   1.66e+04      0.000       1.000       1.000
x5           -2.6e-10    5.8e-05  -4.48e-06      1.000      -0.000       0.000
x6         -1.389e-09      0.000  -1.08e-05      1.000      -0.000       0.000
x7         -2.789e-10   6.01e-05  -4.64e-06      1.000      -0.000       0.000
x8         -2.763e-10   5.99e-05  -4.62e-06      1.000      -0.000       0.000
x9         -2.224e-12    1.6e-06  -1.39e-06      1.000   -3.13e-06    3.13e-06
x10        -1.345e-10   4.12e-05  -3.26e-06      1.000   -8.08e-05    8.08e-05
x11          -2.9e-10   6.12e-05  -4.74e-06      1.000      -0.000       0.000
x12        -2.602e-10   5.82e-05  -4.47e-06      1.000      -0.000       0.000
x13        -2.807e-10   6.03e-05  -4.65e-06      1.000      -0.000       0.000
x14         -1.87e-09      0.000   -1.2e-05      1.000      -0.000       0.000
x15        -2.844e-10   6.05e-05   -4.7e-06      1.000      -0.000       0.000
x16        -7.962e-11    3.2e-05  -2.48e-06      1.000   -6.28e-05    6.28e-05
x17        -2.445e-10   5.61e-05  -4.36e-06      1.000      -0.000       0.000
x18          -6.4e-10   9.15e-05  -6.99e-06      1.000      -0.000       0.000
x19        -2.923e-10   6.14e-05  -4.76e-06      1.000      -0.000       0.000
x20        -4.336e-10   7.41e-05  -5.86e-06      1.000      -0.000       0.000
x21         -4.55e-10    7.5e-05  -6.07e-06      1.000      -0.000       0.000
x22        -3.587e-13   1.42e-11     -0.025      0.980   -2.82e-11    2.75e-11
x23        -1.088e-11   9.56e-11     -0.114      0.909   -1.98e-10    1.76e-10
x24        -2.146e-09      0.000  -1.63e-05      1.000      -0.000       0.000
x25        -1.637e-09      0.000  -1.35e-05      1.000      -0.000       0.000
x26        -3.147e-09      0.000  -1.56e-05      1.000      -0.000       0.000
x27         -2.58e-09      0.000  -1.41e-05      1.000      -0.000       0.000
x28        -2.444e-09      0.000  -1.37e-05      1.000      -0.000       0.000
x29        -1.666e-09      0.000  -1.13e-05      1.000      -0.000       0.000
ar.L1         -0.4923    5.1e-10  -9.65e+08      0.000      -0.492      -0.492
ar.L2         -0.1923   2.96e-10  -6.49e+08      0.000      -0.192      -0.192
ar.L3         -0.0462    1.4e-10  -3.29e+08      0.000      -0.046      -0.046
ma.L1         -0.7077   1.16e-09  -6.12e+08      0.000      -0.708      -0.708
sigma2       8.99e-11   6.96e-11      1.291      0.197   -4.66e-11    2.26e-10
===================================================================================
Ljung-Box (L1) (Q):                  54.06   Jarque-Bera (JB):           4126495.58
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.00   Skew:                             5.48
Prob(H) (two-sided):                  0.00   Kurtosis:                       353.58
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number 2.01e+30. Standard errors may be unstable.
ARIMA order: (3, 3, 1) 

Epoch 1/500

Epoch 00001: val_loss improved from inf to 0.04315, saving model to LSTM8.h5
10/10 - 3s - loss: 1.3932 - val_loss: 0.0432 - lr: 0.0010 - 3s/epoch - 341ms/step
Epoch 2/500

Epoch 00002: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.3430 - val_loss: 0.0433 - lr: 0.0010 - 68ms/epoch - 7ms/step
Epoch 3/500

Epoch 00003: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.2911 - val_loss: 0.0435 - lr: 0.0010 - 69ms/epoch - 7ms/step
Epoch 4/500

Epoch 00004: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.2357 - val_loss: 0.0440 - lr: 0.0010 - 77ms/epoch - 8ms/step
Epoch 5/500

Epoch 00005: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.1792 - val_loss: 0.0446 - lr: 0.0010 - 72ms/epoch - 7ms/step
Epoch 6/500

Epoch 00006: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.

Epoch 00006: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.1259 - val_loss: 0.0452 - lr: 0.0010 - 68ms/epoch - 7ms/step
Epoch 7/500

Epoch 00007: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0918 - val_loss: 0.0453 - lr: 1.0000e-04 - 66ms/epoch - 7ms/step
Epoch 8/500

Epoch 00008: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0874 - val_loss: 0.0454 - lr: 1.0000e-04 - 76ms/epoch - 8ms/step
Epoch 9/500

Epoch 00009: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0832 - val_loss: 0.0455 - lr: 1.0000e-04 - 81ms/epoch - 8ms/step
Epoch 10/500

Epoch 00010: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0791 - val_loss: 0.0455 - lr: 1.0000e-04 - 66ms/epoch - 7ms/step
Epoch 11/500

Epoch 00011: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.

Epoch 00011: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0751 - val_loss: 0.0456 - lr: 1.0000e-04 - 72ms/epoch - 7ms/step
Epoch 12/500

Epoch 00012: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0723 - val_loss: 0.0456 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 13/500

Epoch 00013: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0719 - val_loss: 0.0456 - lr: 1.0000e-05 - 77ms/epoch - 8ms/step
Epoch 14/500

Epoch 00014: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0715 - val_loss: 0.0456 - lr: 1.0000e-05 - 87ms/epoch - 9ms/step
Epoch 15/500

Epoch 00015: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0711 - val_loss: 0.0456 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 16/500

Epoch 00016: ReduceLROnPlateau reducing learning rate to 1e-05.

Epoch 00016: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0708 - val_loss: 0.0457 - lr: 1.0000e-05 - 80ms/epoch - 8ms/step
Epoch 17/500

Epoch 00017: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0704 - val_loss: 0.0457 - lr: 1.0000e-05 - 83ms/epoch - 8ms/step
Epoch 18/500

Epoch 00018: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0700 - val_loss: 0.0457 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 19/500

Epoch 00019: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0696 - val_loss: 0.0457 - lr: 1.0000e-05 - 70ms/epoch - 7ms/step
Epoch 20/500

Epoch 00020: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0692 - val_loss: 0.0457 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 21/500

Epoch 00021: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0688 - val_loss: 0.0457 - lr: 1.0000e-05 - 75ms/epoch - 7ms/step
Epoch 22/500

Epoch 00022: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0684 - val_loss: 0.0457 - lr: 1.0000e-05 - 75ms/epoch - 8ms/step
Epoch 23/500

Epoch 00023: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0680 - val_loss: 0.0457 - lr: 1.0000e-05 - 85ms/epoch - 8ms/step
Epoch 24/500

Epoch 00024: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0677 - val_loss: 0.0457 - lr: 1.0000e-05 - 77ms/epoch - 8ms/step
Epoch 25/500

Epoch 00025: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0673 - val_loss: 0.0457 - lr: 1.0000e-05 - 88ms/epoch - 9ms/step
Epoch 26/500

Epoch 00026: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0669 - val_loss: 0.0457 - lr: 1.0000e-05 - 72ms/epoch - 7ms/step
Epoch 27/500

Epoch 00027: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0665 - val_loss: 0.0457 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 28/500

Epoch 00028: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0661 - val_loss: 0.0458 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 29/500

Epoch 00029: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0657 - val_loss: 0.0458 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 30/500

Epoch 00030: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0653 - val_loss: 0.0458 - lr: 1.0000e-05 - 74ms/epoch - 7ms/step
Epoch 31/500

Epoch 00031: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0649 - val_loss: 0.0458 - lr: 1.0000e-05 - 66ms/epoch - 7ms/step
Epoch 32/500

Epoch 00032: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0646 - val_loss: 0.0458 - lr: 1.0000e-05 - 65ms/epoch - 7ms/step
Epoch 33/500

Epoch 00033: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0642 - val_loss: 0.0458 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 34/500

Epoch 00034: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0638 - val_loss: 0.0458 - lr: 1.0000e-05 - 67ms/epoch - 7ms/step
Epoch 35/500

Epoch 00035: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0634 - val_loss: 0.0458 - lr: 1.0000e-05 - 93ms/epoch - 9ms/step
Epoch 36/500

Epoch 00036: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0630 - val_loss: 0.0458 - lr: 1.0000e-05 - 90ms/epoch - 9ms/step
Epoch 37/500

Epoch 00037: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0626 - val_loss: 0.0458 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 38/500

Epoch 00038: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0623 - val_loss: 0.0458 - lr: 1.0000e-05 - 83ms/epoch - 8ms/step
Epoch 39/500

Epoch 00039: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0619 - val_loss: 0.0458 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 40/500

Epoch 00040: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0615 - val_loss: 0.0459 - lr: 1.0000e-05 - 80ms/epoch - 8ms/step
Epoch 41/500

Epoch 00041: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0611 - val_loss: 0.0459 - lr: 1.0000e-05 - 64ms/epoch - 6ms/step
Epoch 42/500

Epoch 00042: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0607 - val_loss: 0.0459 - lr: 1.0000e-05 - 76ms/epoch - 8ms/step
Epoch 43/500

Epoch 00043: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0603 - val_loss: 0.0459 - lr: 1.0000e-05 - 89ms/epoch - 9ms/step
Epoch 44/500

Epoch 00044: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0600 - val_loss: 0.0459 - lr: 1.0000e-05 - 71ms/epoch - 7ms/step
Epoch 45/500

Epoch 00045: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0596 - val_loss: 0.0459 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 46/500

Epoch 00046: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0592 - val_loss: 0.0459 - lr: 1.0000e-05 - 68ms/epoch - 7ms/step
Epoch 47/500

Epoch 00047: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0588 - val_loss: 0.0459 - lr: 1.0000e-05 - 73ms/epoch - 7ms/step
Epoch 48/500

Epoch 00048: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0585 - val_loss: 0.0459 - lr: 1.0000e-05 - 69ms/epoch - 7ms/step
Epoch 49/500

Epoch 00049: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0581 - val_loss: 0.0459 - lr: 1.0000e-05 - 78ms/epoch - 8ms/step
Epoch 50/500

Epoch 00050: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0577 - val_loss: 0.0459 - lr: 1.0000e-05 - 81ms/epoch - 8ms/step
Epoch 51/500

Epoch 00051: val_loss did not improve from 0.04315
10/10 - 0s - loss: 1.0573 - val_loss: 0.0459 - lr: 1.0000e-05 - 94ms/epoch - 9ms/step
Epoch 00051: early stopping

SMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	49.63% Accuracy
MSE:	 30.79397335917816 
RMSE:	 5.549231780992587 
MAPE:	 4.345848876898189

EMA
Prediction vs Close:		55.22% Accuracy
Prediction vs Prediction:	48.13% Accuracy
MSE:	 32.37277762407691 
RMSE:	 5.689708043834667 
MAPE:	 4.4297291061987245

WMA
Prediction vs Close:		54.1% Accuracy
Prediction vs Prediction:	47.01% Accuracy
MSE:	 58.067607397948805 
RMSE:	 7.620210456276704 
MAPE:	 6.244282675104111

DEMA
Prediction vs Close:		53.36% Accuracy
Prediction vs Prediction:	44.4% Accuracy
MSE:	 166.4719121939062 
RMSE:	 12.902399474280209 
MAPE:	 11.649540302125361
KAMA
KAMA([input_arrays], [timeperiod=30])

Kaufman Adaptive Moving Average (Overlap Studies)

Inputs:
    price: (any ndarray)
Parameters:
    timeperiod: 30
Outputs:
    real
18

Working on KAMA predictions
parameters used :  808 269
Performing stepwise search to minimize aic
 ARIMA(1,3,1)(0,0,0)[0]             : AIC=-16989.104, Time=3.73 sec
 ARIMA(0,3,0)(0,0,0)[0]             : AIC=-14558.591, Time=5.52 sec
 ARIMA(1,3,0)(0,0,0)[0]             : AIC=-16779.655, Time=10.82 sec
 ARIMA(0,3,1)(0,0,0)[0]             : AIC=-14556.590, Time=8.55 sec
 ARIMA(2,3,1)(0,0,0)[0]             : AIC=-16989.430, Time=3.57 sec
 ARIMA(2,3,0)(0,0,0)[0]             : AIC=-16990.286, Time=3.65 sec
 ARIMA(3,3,0)(0,0,0)[0]             : AIC=-16988.543, Time=4.36 sec
 ARIMA(3,3,1)(0,0,0)[0]             : AIC=-16987.154, Time=4.11 sec
 ARIMA(2,3,0)(0,0,0)[0] intercept   : AIC=-16533.935, Time=16.02 sec

Best model:  ARIMA(2,3,0)(0,0,0)[0]          
Total fit time: 60.350 seconds
                               SARIMAX Results                                
==============================================================================
Dep. Variable:                      y   No. Observations:                  808
Model:               SARIMAX(2, 3, 0)   Log Likelihood                8527.143
Date:                Sun, 12 Dec 2021   AIC                         -16990.286
Time:                        19:48:55   BIC                         -16840.179
Sample:                             0   HQIC                        -16932.639
                                - 808                                         
Covariance Type:                  opg                                         
==============================================================================
                 coef    std err          z      P>|z|      [0.025      0.975]
------------------------------------------------------------------------------
x1           -1.1e-16        nan        nan        nan         nan         nan
x2         -3.811e-16         -0        inf      0.000   -3.81e-16   -3.81e-16
x3          8.776e-16   4.38e-27      2e+11      0.000    8.78e-16    8.78e-16
x4             1.0000   4.36e-27   2.29e+26      0.000       1.000       1.000
x5          6.686e-16   4.14e-27   1.61e+11      0.000    6.69e-16    6.69e-16
x6         -5.238e-17   9.44e-27  -5.55e+09      0.000   -5.24e-17   -5.24e-17
x7         -1.709e-16   4.37e-27  -3.91e+10      0.000   -1.71e-16   -1.71e-16
x8          1.439e-15   4.33e-27   3.32e+11      0.000    1.44e-15    1.44e-15
x9         -2.924e-16   5.73e-28   -5.1e+11      0.000   -2.92e-16   -2.92e-16
x10        -1.028e-16   1.78e-27  -5.76e+10      0.000   -1.03e-16   -1.03e-16
x11        -4.338e-16   4.31e-27  -1.01e+11      0.000   -4.34e-16   -4.34e-16
x12          1.72e-16   4.33e-27   3.97e+10      0.000    1.72e-16    1.72e-16
x13        -3.011e-16   4.36e-27  -6.91e+10      0.000   -3.01e-16   -3.01e-16
x14        -2.611e-16   1.27e-26  -2.06e+10      0.000   -2.61e-16   -2.61e-16
x15          1.53e-14   4.46e-27   3.43e+12      0.000    1.53e-14    1.53e-14
x16        -1.401e-14   5.45e-27  -2.57e+12      0.000    -1.4e-14    -1.4e-14
x17         2.316e-14   4.12e-27   5.62e+12      0.000    2.32e-14    2.32e-14
x18        -3.727e-15   3.71e-27  -1.01e+12      0.000   -3.73e-15   -3.73e-15
x19        -1.361e-14   4.94e-27  -2.75e+12      0.000   -1.36e-14   -1.36e-14
x20        -5.277e-15   6.08e-27  -8.68e+11      0.000   -5.28e-15   -5.28e-15
x21         1.178e-18   3.12e-27   3.77e+08      0.000    1.18e-18    1.18e-18
x22        -8.779e-17   1.74e-29  -5.05e+12      0.000   -8.78e-17   -8.78e-17
x23         3.183e-17   5.91e-29   5.39e+11      0.000    3.18e-17    3.18e-17
x24        -1.683e-16   1.41e-26  -1.19e+10      0.000   -1.68e-16   -1.68e-16
x25         8.988e-17   1.48e-30   6.08e+13      0.000    8.99e-17    8.99e-17
x26         4.435e-17   1.58e-26    2.8e+09      0.000    4.44e-17    4.44e-17
x27         1.538e-16   8.87e-27   1.73e+10      0.000    1.54e-16    1.54e-16
x28         1.635e-16   1.22e-26   1.34e+10      0.000    1.63e-16    1.63e-16
x29         1.474e-16   6.34e-27   2.33e+10      0.000    1.47e-16    1.47e-16
ar.L1         -0.9879   1.21e-22  -8.16e+21      0.000      -0.988      -0.988
ar.L2         -0.4879   1.29e-22  -3.79e+21      0.000      -0.488      -0.488
sigma2          1e-10   6.99e-11      1.432      0.152   -3.69e-11    2.37e-10
===================================================================================
Ljung-Box (L1) (Q):                  57.29   Jarque-Bera (JB):            559955.86
Prob(Q):                              0.00   Prob(JB):                         0.00
Heteroskedasticity (H):               0.13   Skew:                             0.64
Prob(H) (two-sided):                  0.00   Kurtosis:                       132.20
===================================================================================

Warnings:
[1] Covariance matrix calculated using the outer product of gradients (complex-step).
[2] Covariance matrix is singular or near-singular, with condition number    inf. Standard errors may be unstable.

/usr/local/lib/python3.7/dist-packages/statsmodels/tsa/statespace/mlemodel.py:2968: RuntimeWarning: divide by zero encountered in true_divide
  return self.params / self.bse

Architecture Used¶

from google.colab import files
import cv2
uploaded = files.upload()

Saving Experiment8.png to Experiment8 (1).png

img = cv2.imread('Experiment8.png')
plt.figure(figsize=(20,10))
plt.axis("off")
plt.title('LSTM Architecture '+imgfile,fontsize=18)
plt.imshow(img)

<matplotlib.image.AxesImage at 0x7fa5ce50e910>

Model Plots¶

for i in range(len(list(simulation8.keys()))):
  SIM = list(simulation8.keys())[i]
  plot_train(simulation8,SIM)
  plot_test(simulation8,SIM)

----- Train RMSE for SMA ----- 16.984837129738686
----- Train_MSE_LSTM for SMA ----- 288.48469232374987
----- Train MAE LSTM for SMA ----- 16.91967470811145

----- Test RMSE for SMA----- 5.549231780992587
----- Test_MSE_LSTM for SMA----- 30.79397335917816
----- Test_MAE_LSTM for SMA----- 4.345848876898189

----- Train RMSE for EMA ----- 24.064453268878548
----- Train_MSE_LSTM for EMA ----- 579.0979111300394
----- Train MAE LSTM for EMA ----- 24.05741292651337

----- Test RMSE for EMA----- 5.689708043834667
----- Test_MSE_LSTM for EMA----- 32.37277762407691
----- Test_MAE_LSTM for EMA----- 4.4297291061987245

----- Train RMSE for WMA ----- 21.99024849687679
----- Train_MSE_LSTM for WMA ----- 483.571028954392
----- Train MAE LSTM for WMA ----- 21.95148728153493

----- Test RMSE for WMA----- 7.620210456276704
----- Test_MSE_LSTM for WMA----- 58.067607397948805
----- Test_MAE_LSTM for WMA----- 6.244282675104111

----- Train RMSE for DEMA ----- 24.365605462542323
----- Train_MSE_LSTM for DEMA ----- 593.6827295562723
----- Train MAE LSTM for DEMA ----- 24.332061871443646

----- Test RMSE for DEMA----- 12.902399474280209
----- Test_MSE_LSTM for DEMA----- 166.4719121939062
----- Test_MAE_LSTM for DEMA----- 11.649540302125361

----- Train RMSE for KAMA ----- 17.353875298772294
----- Train_MSE_LSTM for KAMA ----- 301.1569878853392
----- Train MAE LSTM for KAMA ----- 17.33646524542629

----- Test RMSE for KAMA----- 4.220769393485087
----- Test_MSE_LSTM for KAMA----- 17.81489427298047
----- Test_MAE_LSTM for KAMA----- 3.4008273908825086

List of RMSE, MSE & MAE scores for Test data¶

import json
with open('simulation1_data.json') as json_file:
    simulation1 = json.load(json_file)

with open('simulation2_data.json') as json_file:
    simulation2 = json.load(json_file)

with open('simulation3_data.json') as json_file:
    simulation3 = json.load(json_file)

with open('simulation4_data.json') as json_file:
    simulation4 = json.load(json_file)

with open('simulation5_data.json') as json_file:
    simulation5 = json.load(json_file)

with open('simulation6_data.json') as json_file:
    simulation6 = json.load(json_file)

with open('simulation7_data.json') as json_file:
    simulation7 = json.load(json_file)

with open('simulation8_data.json') as json_file:
    simulation8 = json.load(json_file)

text = 'Stock with Full dataset'
simulations = [simulation1,simulation2,simulation3,simulation4,simulation5,simulation6,simulation7,simulation8]
for i,simulation in enumerate(simulations):
  for ma in simulation.keys():
    print(text+'Experiment ',i+1,' for MA :',ma,'the MSE  is: ',simulation[ma]['final']['mse'])
    print(text+'Experiment ',i+1,' for MA :',ma,'the RMSE is: ',simulation[ma]['final']['rmse'])
    print(text+'Experiment ',i+1,' for MA :',ma,'the MAE is: ',simulation[ma]['final']['mae'])

Stock with Full datasetExperiment  1  for MA : SMA the MSE  is:  29.509403666146007
Stock with Full datasetExperiment  1  for MA : SMA the RMSE is:  5.432255854260365
Stock with Full datasetExperiment  1  for MA : SMA the MAE is:  4.5288133477558885
Stock with Full datasetExperiment  1  for MA : EMA the MSE  is:  28.603272766421263
Stock with Full datasetExperiment  1  for MA : EMA the RMSE is:  5.348202760406646
Stock with Full datasetExperiment  1  for MA : EMA the MAE is:  4.3952252144553965
Stock with Full datasetExperiment  1  for MA : WMA the MSE  is:  80.72598349686672
Stock with Full datasetExperiment  1  for MA : WMA the RMSE is:  8.9847639644493
Stock with Full datasetExperiment  1  for MA : WMA the MAE is:  7.266216353433966
Stock with Full datasetExperiment  1  for MA : DEMA the MSE  is:  74.8946292448382
Stock with Full datasetExperiment  1  for MA : DEMA the RMSE is:  8.654168316183721
Stock with Full datasetExperiment  1  for MA : DEMA the MAE is:  7.175854729849037
Stock with Full datasetExperiment  1  for MA : KAMA the MSE  is:  23.77011386693893
Stock with Full datasetExperiment  1  for MA : KAMA the RMSE is:  4.87546037487117
Stock with Full datasetExperiment  1  for MA : KAMA the MAE is:  3.900500517739451
Stock with Full datasetExperiment  1  for MA : MIDPOINT the MSE  is:  53.557107319764015
Stock with Full datasetExperiment  1  for MA : MIDPOINT the RMSE is:  7.318272153983071
Stock with Full datasetExperiment  1  for MA : MIDPOINT the MAE is:  6.3365268769325365
Stock with Full datasetExperiment  1  for MA : T3 the MSE  is:  44.09609147416104
Stock with Full datasetExperiment  1  for MA : T3 the RMSE is:  6.640488797834165
Stock with Full datasetExperiment  1  for MA : T3 the MAE is:  5.406095596816415
Stock with Full datasetExperiment  1  for MA : TEMA the MSE  is:  9.564405293897392
Stock with Full datasetExperiment  1  for MA : TEMA the RMSE is:  3.0926372716336124
Stock with Full datasetExperiment  1  for MA : TEMA the MAE is:  2.44888799215368
Stock with Full datasetExperiment  2  for MA : SMA the MSE  is:  75.20110458138421
Stock with Full datasetExperiment  2  for MA : SMA the RMSE is:  8.67185704341257
Stock with Full datasetExperiment  2  for MA : SMA the MAE is:  7.0799160587584336
Stock with Full datasetExperiment  2  for MA : EMA the MSE  is:  61.82384712230415
Stock with Full datasetExperiment  2  for MA : EMA the RMSE is:  7.862814198638052
Stock with Full datasetExperiment  2  for MA : EMA the MAE is:  6.504666247736678
Stock with Full datasetExperiment  2  for MA : WMA the MSE  is:  78.06346997131263
Stock with Full datasetExperiment  2  for MA : WMA the RMSE is:  8.835353415190172
Stock with Full datasetExperiment  2  for MA : WMA the MAE is:  6.948265794170055
Stock with Full datasetExperiment  2  for MA : DEMA the MSE  is:  153.59400995187858
Stock with Full datasetExperiment  2  for MA : DEMA the RMSE is:  12.39330504554288
Stock with Full datasetExperiment  2  for MA : DEMA the MAE is:  11.203775482220726
Stock with Full datasetExperiment  2  for MA : KAMA the MSE  is:  121.28941541171922
Stock with Full datasetExperiment  2  for MA : KAMA the RMSE is:  11.013147388994629
Stock with Full datasetExperiment  2  for MA : KAMA the MAE is:  9.175643045864026
Stock with Full datasetExperiment  2  for MA : MIDPOINT the MSE  is:  110.09412594018622
Stock with Full datasetExperiment  2  for MA : MIDPOINT the RMSE is:  10.492574800314088
Stock with Full datasetExperiment  2  for MA : MIDPOINT the MAE is:  8.796456301428389
Stock with Full datasetExperiment  2  for MA : T3 the MSE  is:  225.73907153615718
Stock with Full datasetExperiment  2  for MA : T3 the RMSE is:  15.024615520410403
Stock with Full datasetExperiment  2  for MA : T3 the MAE is:  12.611725131734374
Stock with Full datasetExperiment  2  for MA : TEMA the MSE  is:  157.04980120863047
Stock with Full datasetExperiment  2  for MA : TEMA the RMSE is:  12.531951213144364
Stock with Full datasetExperiment  2  for MA : TEMA the MAE is:  11.294114614846999
Stock with Full datasetExperiment  3  for MA : SMA the MSE  is:  32.725767438505336
Stock with Full datasetExperiment  3  for MA : SMA the RMSE is:  5.7206439706125165
Stock with Full datasetExperiment  3  for MA : SMA the MAE is:  4.798603095387009
Stock with Full datasetExperiment  3  for MA : EMA the MSE  is:  143.9522591181831
Stock with Full datasetExperiment  3  for MA : EMA the RMSE is:  11.998010631691534
Stock with Full datasetExperiment  3  for MA : EMA the MAE is:  10.07848404711658
Stock with Full datasetExperiment  3  for MA : WMA the MSE  is:  24.586224407987817
Stock with Full datasetExperiment  3  for MA : WMA the RMSE is:  4.958449798877449
Stock with Full datasetExperiment  3  for MA : WMA the MAE is:  3.970226889097132
Stock with Full datasetExperiment  3  for MA : DEMA the MSE  is:  207.2547601932076
Stock with Full datasetExperiment  3  for MA : DEMA the RMSE is:  14.3963453762824
Stock with Full datasetExperiment  3  for MA : DEMA the MAE is:  12.894635987621164
Stock with Full datasetExperiment  3  for MA : KAMA the MSE  is:  23.743754657069395
Stock with Full datasetExperiment  3  for MA : KAMA the RMSE is:  4.872756371610364
Stock with Full datasetExperiment  3  for MA : KAMA the MAE is:  3.7850733762502107
Stock with Full datasetExperiment  3  for MA : MIDPOINT the MSE  is:  35.62442093531873
Stock with Full datasetExperiment  3  for MA : MIDPOINT the RMSE is:  5.968619684258559
Stock with Full datasetExperiment  3  for MA : MIDPOINT the MAE is:  5.0490603478808165
Stock with Full datasetExperiment  3  for MA : T3 the MSE  is:  103.73535640918065
Stock with Full datasetExperiment  3  for MA : T3 the RMSE is:  10.185055542763655
Stock with Full datasetExperiment  3  for MA : T3 the MAE is:  8.016244139827235
Stock with Full datasetExperiment  3  for MA : TEMA the MSE  is:  39.894741171517865
Stock with Full datasetExperiment  3  for MA : TEMA the RMSE is:  6.316228397668807
Stock with Full datasetExperiment  3  for MA : TEMA the MAE is:  5.481705479796751
Stock with Full datasetExperiment  4  for MA : SMA the MSE  is:  19.776724587061057
Stock with Full datasetExperiment  4  for MA : SMA the RMSE is:  4.447102943159856
Stock with Full datasetExperiment  4  for MA : SMA the MAE is:  3.587879520041786
Stock with Full datasetExperiment  4  for MA : EMA the MSE  is:  31.621751516368622
Stock with Full datasetExperiment  4  for MA : EMA the RMSE is:  5.623322106759368
Stock with Full datasetExperiment  4  for MA : EMA the MAE is:  4.355106062590965
Stock with Full datasetExperiment  4  for MA : WMA the MSE  is:  52.4753296205182
Stock with Full datasetExperiment  4  for MA : WMA the RMSE is:  7.2439857551294375
Stock with Full datasetExperiment  4  for MA : WMA the MAE is:  5.852253139584933
Stock with Full datasetExperiment  4  for MA : DEMA the MSE  is:  146.44755629127866
Stock with Full datasetExperiment  4  for MA : DEMA the RMSE is:  12.10155181335347
Stock with Full datasetExperiment  4  for MA : DEMA the MAE is:  10.943210296434415
Stock with Full datasetExperiment  4  for MA : KAMA the MSE  is:  19.64215945229788
Stock with Full datasetExperiment  4  for MA : KAMA the RMSE is:  4.4319475913302355
Stock with Full datasetExperiment  4  for MA : KAMA the MAE is:  3.5686191181651687
Stock with Full datasetExperiment  4  for MA : MIDPOINT the MSE  is:  19.83404242536117
Stock with Full datasetExperiment  4  for MA : MIDPOINT the RMSE is:  4.453542682557468
Stock with Full datasetExperiment  4  for MA : MIDPOINT the MAE is:  3.5743844299716057
Stock with Full datasetExperiment  4  for MA : T3 the MSE  is:  70.66866288490243
Stock with Full datasetExperiment  4  for MA : T3 the RMSE is:  8.406465540576637
Stock with Full datasetExperiment  4  for MA : T3 the MAE is:  6.802843731006552
Stock with Full datasetExperiment  4  for MA : TEMA the MSE  is:  14.860699364166678
Stock with Full datasetExperiment  4  for MA : TEMA the RMSE is:  3.8549577642519868
Stock with Full datasetExperiment  4  for MA : TEMA the MAE is:  3.1502795604602833
Stock with Full datasetExperiment  5  for MA : SMA the MSE  is:  34.39169744803393
Stock with Full datasetExperiment  5  for MA : SMA the RMSE is:  5.864443490053761
Stock with Full datasetExperiment  5  for MA : SMA the MAE is:  4.893666026892695
Stock with Full datasetExperiment  5  for MA : EMA the MSE  is:  73.04930062485933
Stock with Full datasetExperiment  5  for MA : EMA the RMSE is:  8.546888359213506
Stock with Full datasetExperiment  5  for MA : EMA the MAE is:  6.613879572809731
Stock with Full datasetExperiment  5  for MA : WMA the MSE  is:  70.35376938042184
Stock with Full datasetExperiment  5  for MA : WMA the RMSE is:  8.387715385039114
Stock with Full datasetExperiment  5  for MA : WMA the MAE is:  6.8547592718484545
Stock with Full datasetExperiment  5  for MA : DEMA the MSE  is:  70.24761196199488
Stock with Full datasetExperiment  5  for MA : DEMA the RMSE is:  8.381384847505505
Stock with Full datasetExperiment  5  for MA : DEMA the MAE is:  6.862692730259403
Stock with Full datasetExperiment  5  for MA : KAMA the MSE  is:  27.01407660930758
Stock with Full datasetExperiment  5  for MA : KAMA the RMSE is:  5.1975067685677505
Stock with Full datasetExperiment  5  for MA : KAMA the MAE is:  4.263533603346384
Stock with Full datasetExperiment  5  for MA : MIDPOINT the MSE  is:  37.16076795716489
Stock with Full datasetExperiment  5  for MA : MIDPOINT the RMSE is:  6.095963250969029
Stock with Full datasetExperiment  5  for MA : MIDPOINT the MAE is:  5.0853544537748006
Stock with Full datasetExperiment  5  for MA : T3 the MSE  is:  104.49209322707955
Stock with Full datasetExperiment  5  for MA : T3 the RMSE is:  10.222137409909903
Stock with Full datasetExperiment  5  for MA : T3 the MAE is:  7.958642954509092
Stock with Full datasetExperiment  5  for MA : TEMA the MSE  is:  72.80283545670305
Stock with Full datasetExperiment  5  for MA : TEMA the RMSE is:  8.532457761788397
Stock with Full datasetExperiment  5  for MA : TEMA the MAE is:  7.653550657820228
Stock with Full datasetExperiment  6  for MA : SMA the MSE  is:  75.03401716737034
Stock with Full datasetExperiment  6  for MA : SMA the RMSE is:  8.662217797271685
Stock with Full datasetExperiment  6  for MA : SMA the MAE is:  7.077228582293258
Stock with Full datasetExperiment  6  for MA : EMA the MSE  is:  70.28436187942754
Stock with Full datasetExperiment  6  for MA : EMA the RMSE is:  8.383576914386099
Stock with Full datasetExperiment  6  for MA : EMA the MAE is:  6.876111393338704
Stock with Full datasetExperiment  6  for MA : WMA the MSE  is:  70.57086226636761
Stock with Full datasetExperiment  6  for MA : WMA the RMSE is:  8.400646538592587
Stock with Full datasetExperiment  6  for MA : WMA the MAE is:  6.6664001460728475
Stock with Full datasetExperiment  6  for MA : DEMA the MSE  is:  329.6035699397079
Stock with Full datasetExperiment  6  for MA : DEMA the RMSE is:  18.15498746735199
Stock with Full datasetExperiment  6  for MA : DEMA the MAE is:  16.799244301034683
Stock with Full datasetExperiment  6  for MA : KAMA the MSE  is:  103.27437965196852
Stock with Full datasetExperiment  6  for MA : KAMA the RMSE is:  10.162400289890599
Stock with Full datasetExperiment  6  for MA : KAMA the MAE is:  8.510636158449836
Stock with Full datasetExperiment  6  for MA : MIDPOINT the MSE  is:  97.31838139819504
Stock with Full datasetExperiment  6  for MA : MIDPOINT the RMSE is:  9.86500792692003
Stock with Full datasetExperiment  6  for MA : MIDPOINT the MAE is:  8.251875922025462
Stock with Full datasetExperiment  6  for MA : T3 the MSE  is:  154.17386959926716
Stock with Full datasetExperiment  6  for MA : T3 the RMSE is:  12.41667707558134
Stock with Full datasetExperiment  6  for MA : T3 the MAE is:  10.12780101556255
Stock with Full datasetExperiment  6  for MA : TEMA the MSE  is:  87.38626729945001
Stock with Full datasetExperiment  6  for MA : TEMA the RMSE is:  9.348062221629144
Stock with Full datasetExperiment  6  for MA : TEMA the MAE is:  8.358174186376312
Stock with Full datasetExperiment  7  for MA : SMA the MSE  is:  44.65212926265077
Stock with Full datasetExperiment  7  for MA : SMA the RMSE is:  6.682224873696692
Stock with Full datasetExperiment  7  for MA : SMA the MAE is:  5.204686480071648
Stock with Full datasetExperiment  7  for MA : EMA the MSE  is:  45.539825469272486
Stock with Full datasetExperiment  7  for MA : EMA the RMSE is:  6.748320196113436
Stock with Full datasetExperiment  7  for MA : EMA the MAE is:  5.43245952292463
Stock with Full datasetExperiment  7  for MA : WMA the MSE  is:  42.30488040231578
Stock with Full datasetExperiment  7  for MA : WMA the RMSE is:  6.504220199402522
Stock with Full datasetExperiment  7  for MA : WMA the MAE is:  5.010195929360332
Stock with Full datasetExperiment  7  for MA : DEMA the MSE  is:  23.305922116020078
Stock with Full datasetExperiment  7  for MA : DEMA the RMSE is:  4.827620751055335
Stock with Full datasetExperiment  7  for MA : DEMA the MAE is:  3.7452201197397774
Stock with Full datasetExperiment  7  for MA : KAMA the MSE  is:  18.082341646298453
Stock with Full datasetExperiment  7  for MA : KAMA the RMSE is:  4.252333670621163
Stock with Full datasetExperiment  7  for MA : KAMA the MAE is:  3.4333194517527637
Stock with Full datasetExperiment  7  for MA : MIDPOINT the MSE  is:  91.59813707600279
Stock with Full datasetExperiment  7  for MA : MIDPOINT the RMSE is:  9.57069156727991
Stock with Full datasetExperiment  7  for MA : MIDPOINT the MAE is:  7.718313236319782
Stock with Full datasetExperiment  7  for MA : T3 the MSE  is:  145.19295971499469
Stock with Full datasetExperiment  7  for MA : T3 the RMSE is:  12.049604131049065
Stock with Full datasetExperiment  7  for MA : T3 the MAE is:  9.875885491811884
Stock with Full datasetExperiment  7  for MA : TEMA the MSE  is:  41.1158513706741
Stock with Full datasetExperiment  7  for MA : TEMA the RMSE is:  6.412164328109044
Stock with Full datasetExperiment  7  for MA : TEMA the MAE is:  5.720374187090847
Stock with Full datasetExperiment  8  for MA : SMA the MSE  is:  30.79397335917816
Stock with Full datasetExperiment  8  for MA : SMA the RMSE is:  5.549231780992587
Stock with Full datasetExperiment  8  for MA : SMA the MAE is:  4.345848876898189
Stock with Full datasetExperiment  8  for MA : EMA the MSE  is:  32.37277762407691
Stock with Full datasetExperiment  8  for MA : EMA the RMSE is:  5.689708043834667
Stock with Full datasetExperiment  8  for MA : EMA the MAE is:  4.4297291061987245
Stock with Full datasetExperiment  8  for MA : WMA the MSE  is:  58.067607397948805
Stock with Full datasetExperiment  8  for MA : WMA the RMSE is:  7.620210456276704
Stock with Full datasetExperiment  8  for MA : WMA the MAE is:  6.244282675104111
Stock with Full datasetExperiment  8  for MA : DEMA the MSE  is:  166.4719121939062
Stock with Full datasetExperiment  8  for MA : DEMA the RMSE is:  12.902399474280209
Stock with Full datasetExperiment  8  for MA : DEMA the MAE is:  11.649540302125361
Stock with Full datasetExperiment  8  for MA : KAMA the MSE  is:  17.81489427298047
Stock with Full datasetExperiment  8  for MA : KAMA the RMSE is:  4.220769393485087
Stock with Full datasetExperiment  8  for MA : KAMA the MAE is:  3.4008273908825086
Stock with Full datasetExperiment  8  for MA : MIDPOINT the MSE  is:  18.523766068694844
Stock with Full datasetExperiment  8  for MA : MIDPOINT the RMSE is:  4.303924496165662
Stock with Full datasetExperiment  8  for MA : MIDPOINT the MAE is:  3.4879205441290337
Stock with Full datasetExperiment  8  for MA : T3 the MSE  is:  51.75272426881254
Stock with Full datasetExperiment  8  for MA : T3 the RMSE is:  7.193936632248893
Stock with Full datasetExperiment  8  for MA : T3 the MAE is:  5.759673530885367
Stock with Full datasetExperiment  8  for MA : TEMA the MSE  is:  28.424875173467463
Stock with Full datasetExperiment  8  for MA : TEMA the RMSE is:  5.331498398524327
Stock with Full datasetExperiment  8  for MA : TEMA the MAE is:  4.66633698560039

text = 'Stock with Full dataset '
simulations = [simulation1,simulation2,simulation3,simulation4,simulation5,simulation6,simulation7,simulation8]
for i,simulation in enumerate(simulations):
  for ma in simulation.keys():
    # print(text+'Experiment ',i+1,' for MA :',ma,'the MSE  is: ',simulation[ma]['final']['mse'])
    print(text+'Experiment ',i+1,' for MA :',ma,'the RMSE is: ',simulation[ma]['final']['rmse'])
    # print(text+'Experiment ',i+1,' for MA :',ma,'the MAE is: ',simulation[ma]['final']['mae'])
  for ma in simulation.keys():
    print(text+'Experiment ',i+1,' for MA :',ma,'the MSE  is: ',simulation[ma]['final']['mse'])
    # print(text+'Experiment ',i+1,' for MA :',ma,'the RMSE is: ',simulation[ma]['final']['rmse'])
    # print(text+'Experiment ',i+1,' for MA :',ma,'the MAE is: ',simulation[ma]['final']['mae'])
  for ma in simulation.keys():
    # print(text+'Experiment ',i+1,' for MA :',ma,'the MSE  is: ',simulation[ma]['final']['mse'])
    # print(text+'Experiment ',i+1,' for MA :',ma,'the RMSE is: ',simulation[ma]['final']['rmse'])
    print(text+'Experiment ',i+1,' for MA :',ma,'the MAE is: ',simulation[ma]['final']['mae'])

Stock with Full dataset Experiment  1  for MA : SMA the RMSE is:  5.432255854260365
Stock with Full dataset Experiment  1  for MA : EMA the RMSE is:  5.348202760406646
Stock with Full dataset Experiment  1  for MA : WMA the RMSE is:  8.9847639644493
Stock with Full dataset Experiment  1  for MA : DEMA the RMSE is:  8.654168316183721
Stock with Full dataset Experiment  1  for MA : KAMA the RMSE is:  4.87546037487117
Stock with Full dataset Experiment  1  for MA : MIDPOINT the RMSE is:  7.318272153983071
Stock with Full dataset Experiment  1  for MA : T3 the RMSE is:  6.640488797834165
Stock with Full dataset Experiment  1  for MA : TEMA the RMSE is:  3.0926372716336124
Stock with Full dataset Experiment  1  for MA : SMA the MSE  is:  29.509403666146007
Stock with Full dataset Experiment  1  for MA : EMA the MSE  is:  28.603272766421263
Stock with Full dataset Experiment  1  for MA : WMA the MSE  is:  80.72598349686672
Stock with Full dataset Experiment  1  for MA : DEMA the MSE  is:  74.8946292448382
Stock with Full dataset Experiment  1  for MA : KAMA the MSE  is:  23.77011386693893
Stock with Full dataset Experiment  1  for MA : MIDPOINT the MSE  is:  53.557107319764015
Stock with Full dataset Experiment  1  for MA : T3 the MSE  is:  44.09609147416104
Stock with Full dataset Experiment  1  for MA : TEMA the MSE  is:  9.564405293897392
Stock with Full dataset Experiment  1  for MA : SMA the MAE is:  4.5288133477558885
Stock with Full dataset Experiment  1  for MA : EMA the MAE is:  4.3952252144553965
Stock with Full dataset Experiment  1  for MA : WMA the MAE is:  7.266216353433966
Stock with Full dataset Experiment  1  for MA : DEMA the MAE is:  7.175854729849037
Stock with Full dataset Experiment  1  for MA : KAMA the MAE is:  3.900500517739451
Stock with Full dataset Experiment  1  for MA : MIDPOINT the MAE is:  6.3365268769325365
Stock with Full dataset Experiment  1  for MA : T3 the MAE is:  5.406095596816415
Stock with Full dataset Experiment  1  for MA : TEMA the MAE is:  2.44888799215368
Stock with Full dataset Experiment  2  for MA : SMA the RMSE is:  8.67185704341257
Stock with Full dataset Experiment  2  for MA : EMA the RMSE is:  7.862814198638052
Stock with Full dataset Experiment  2  for MA : WMA the RMSE is:  8.835353415190172
Stock with Full dataset Experiment  2  for MA : DEMA the RMSE is:  12.39330504554288
Stock with Full dataset Experiment  2  for MA : KAMA the RMSE is:  11.013147388994629
Stock with Full dataset Experiment  2  for MA : MIDPOINT the RMSE is:  10.492574800314088
Stock with Full dataset Experiment  2  for MA : T3 the RMSE is:  15.024615520410403
Stock with Full dataset Experiment  2  for MA : TEMA the RMSE is:  12.531951213144364
Stock with Full dataset Experiment  2  for MA : SMA the MSE  is:  75.20110458138421
Stock with Full dataset Experiment  2  for MA : EMA the MSE  is:  61.82384712230415
Stock with Full dataset Experiment  2  for MA : WMA the MSE  is:  78.06346997131263
Stock with Full dataset Experiment  2  for MA : DEMA the MSE  is:  153.59400995187858
Stock with Full dataset Experiment  2  for MA : KAMA the MSE  is:  121.28941541171922
Stock with Full dataset Experiment  2  for MA : MIDPOINT the MSE  is:  110.09412594018622
Stock with Full dataset Experiment  2  for MA : T3 the MSE  is:  225.73907153615718
Stock with Full dataset Experiment  2  for MA : TEMA the MSE  is:  157.04980120863047
Stock with Full dataset Experiment  2  for MA : SMA the MAE is:  7.0799160587584336
Stock with Full dataset Experiment  2  for MA : EMA the MAE is:  6.504666247736678
Stock with Full dataset Experiment  2  for MA : WMA the MAE is:  6.948265794170055
Stock with Full dataset Experiment  2  for MA : DEMA the MAE is:  11.203775482220726
Stock with Full dataset Experiment  2  for MA : KAMA the MAE is:  9.175643045864026
Stock with Full dataset Experiment  2  for MA : MIDPOINT the MAE is:  8.796456301428389
Stock with Full dataset Experiment  2  for MA : T3 the MAE is:  12.611725131734374
Stock with Full dataset Experiment  2  for MA : TEMA the MAE is:  11.294114614846999
Stock with Full dataset Experiment  3  for MA : SMA the RMSE is:  5.7206439706125165
Stock with Full dataset Experiment  3  for MA : EMA the RMSE is:  11.998010631691534
Stock with Full dataset Experiment  3  for MA : WMA the RMSE is:  4.958449798877449
Stock with Full dataset Experiment  3  for MA : DEMA the RMSE is:  14.3963453762824
Stock with Full dataset Experiment  3  for MA : KAMA the RMSE is:  4.872756371610364
Stock with Full dataset Experiment  3  for MA : MIDPOINT the RMSE is:  5.968619684258559
Stock with Full dataset Experiment  3  for MA : T3 the RMSE is:  10.185055542763655
Stock with Full dataset Experiment  3  for MA : TEMA the RMSE is:  6.316228397668807
Stock with Full dataset Experiment  3  for MA : SMA the MSE  is:  32.725767438505336
Stock with Full dataset Experiment  3  for MA : EMA the MSE  is:  143.9522591181831
Stock with Full dataset Experiment  3  for MA : WMA the MSE  is:  24.586224407987817
Stock with Full dataset Experiment  3  for MA : DEMA the MSE  is:  207.2547601932076
Stock with Full dataset Experiment  3  for MA : KAMA the MSE  is:  23.743754657069395
Stock with Full dataset Experiment  3  for MA : MIDPOINT the MSE  is:  35.62442093531873
Stock with Full dataset Experiment  3  for MA : T3 the MSE  is:  103.73535640918065
Stock with Full dataset Experiment  3  for MA : TEMA the MSE  is:  39.894741171517865
Stock with Full dataset Experiment  3  for MA : SMA the MAE is:  4.798603095387009
Stock with Full dataset Experiment  3  for MA : EMA the MAE is:  10.07848404711658
Stock with Full dataset Experiment  3  for MA : WMA the MAE is:  3.970226889097132
Stock with Full dataset Experiment  3  for MA : DEMA the MAE is:  12.894635987621164
Stock with Full dataset Experiment  3  for MA : KAMA the MAE is:  3.7850733762502107
Stock with Full dataset Experiment  3  for MA : MIDPOINT the MAE is:  5.0490603478808165
Stock with Full dataset Experiment  3  for MA : T3 the MAE is:  8.016244139827235
Stock with Full dataset Experiment  3  for MA : TEMA the MAE is:  5.481705479796751
Stock with Full dataset Experiment  4  for MA : SMA the RMSE is:  4.447102943159856
Stock with Full dataset Experiment  4  for MA : EMA the RMSE is:  5.623322106759368
Stock with Full dataset Experiment  4  for MA : WMA the RMSE is:  7.2439857551294375
Stock with Full dataset Experiment  4  for MA : DEMA the RMSE is:  12.10155181335347
Stock with Full dataset Experiment  4  for MA : KAMA the RMSE is:  4.4319475913302355
Stock with Full dataset Experiment  4  for MA : MIDPOINT the RMSE is:  4.453542682557468
Stock with Full dataset Experiment  4  for MA : T3 the RMSE is:  8.406465540576637
Stock with Full dataset Experiment  4  for MA : TEMA the RMSE is:  3.8549577642519868
Stock with Full dataset Experiment  4  for MA : SMA the MSE  is:  19.776724587061057
Stock with Full dataset Experiment  4  for MA : EMA the MSE  is:  31.621751516368622
Stock with Full dataset Experiment  4  for MA : WMA the MSE  is:  52.4753296205182
Stock with Full dataset Experiment  4  for MA : DEMA the MSE  is:  146.44755629127866
Stock with Full dataset Experiment  4  for MA : KAMA the MSE  is:  19.64215945229788
Stock with Full dataset Experiment  4  for MA : MIDPOINT the MSE  is:  19.83404242536117
Stock with Full dataset Experiment  4  for MA : T3 the MSE  is:  70.66866288490243
Stock with Full dataset Experiment  4  for MA : TEMA the MSE  is:  14.860699364166678
Stock with Full dataset Experiment  4  for MA : SMA the MAE is:  3.587879520041786
Stock with Full dataset Experiment  4  for MA : EMA the MAE is:  4.355106062590965
Stock with Full dataset Experiment  4  for MA : WMA the MAE is:  5.852253139584933
Stock with Full dataset Experiment  4  for MA : DEMA the MAE is:  10.943210296434415
Stock with Full dataset Experiment  4  for MA : KAMA the MAE is:  3.5686191181651687
Stock with Full dataset Experiment  4  for MA : MIDPOINT the MAE is:  3.5743844299716057
Stock with Full dataset Experiment  4  for MA : T3 the MAE is:  6.802843731006552
Stock with Full dataset Experiment  4  for MA : TEMA the MAE is:  3.1502795604602833
Stock with Full dataset Experiment  5  for MA : SMA the RMSE is:  5.864443490053761
Stock with Full dataset Experiment  5  for MA : EMA the RMSE is:  8.546888359213506
Stock with Full dataset Experiment  5  for MA : WMA the RMSE is:  8.387715385039114
Stock with Full dataset Experiment  5  for MA : DEMA the RMSE is:  8.381384847505505
Stock with Full dataset Experiment  5  for MA : KAMA the RMSE is:  5.1975067685677505
Stock with Full dataset Experiment  5  for MA : MIDPOINT the RMSE is:  6.095963250969029
Stock with Full dataset Experiment  5  for MA : T3 the RMSE is:  10.222137409909903
Stock with Full dataset Experiment  5  for MA : TEMA the RMSE is:  8.532457761788397
Stock with Full dataset Experiment  5  for MA : SMA the MSE  is:  34.39169744803393
Stock with Full dataset Experiment  5  for MA : EMA the MSE  is:  73.04930062485933
Stock with Full dataset Experiment  5  for MA : WMA the MSE  is:  70.35376938042184
Stock with Full dataset Experiment  5  for MA : DEMA the MSE  is:  70.24761196199488
Stock with Full dataset Experiment  5  for MA : KAMA the MSE  is:  27.01407660930758
Stock with Full dataset Experiment  5  for MA : MIDPOINT the MSE  is:  37.16076795716489
Stock with Full dataset Experiment  5  for MA : T3 the MSE  is:  104.49209322707955
Stock with Full dataset Experiment  5  for MA : TEMA the MSE  is:  72.80283545670305
Stock with Full dataset Experiment  5  for MA : SMA the MAE is:  4.893666026892695
Stock with Full dataset Experiment  5  for MA : EMA the MAE is:  6.613879572809731
Stock with Full dataset Experiment  5  for MA : WMA the MAE is:  6.8547592718484545
Stock with Full dataset Experiment  5  for MA : DEMA the MAE is:  6.862692730259403
Stock with Full dataset Experiment  5  for MA : KAMA the MAE is:  4.263533603346384
Stock with Full dataset Experiment  5  for MA : MIDPOINT the MAE is:  5.0853544537748006
Stock with Full dataset Experiment  5  for MA : T3 the MAE is:  7.958642954509092
Stock with Full dataset Experiment  5  for MA : TEMA the MAE is:  7.653550657820228
Stock with Full dataset Experiment  6  for MA : SMA the RMSE is:  8.662217797271685
Stock with Full dataset Experiment  6  for MA : EMA the RMSE is:  8.383576914386099
Stock with Full dataset Experiment  6  for MA : WMA the RMSE is:  8.400646538592587
Stock with Full dataset Experiment  6  for MA : DEMA the RMSE is:  18.15498746735199
Stock with Full dataset Experiment  6  for MA : KAMA the RMSE is:  10.162400289890599
Stock with Full dataset Experiment  6  for MA : MIDPOINT the RMSE is:  9.86500792692003
Stock with Full dataset Experiment  6  for MA : T3 the RMSE is:  12.41667707558134
Stock with Full dataset Experiment  6  for MA : TEMA the RMSE is:  9.348062221629144
Stock with Full dataset Experiment  6  for MA : SMA the MSE  is:  75.03401716737034
Stock with Full dataset Experiment  6  for MA : EMA the MSE  is:  70.28436187942754
Stock with Full dataset Experiment  6  for MA : WMA the MSE  is:  70.57086226636761
Stock with Full dataset Experiment  6  for MA : DEMA the MSE  is:  329.6035699397079
Stock with Full dataset Experiment  6  for MA : KAMA the MSE  is:  103.27437965196852
Stock with Full dataset Experiment  6  for MA : MIDPOINT the MSE  is:  97.31838139819504
Stock with Full dataset Experiment  6  for MA : T3 the MSE  is:  154.17386959926716
Stock with Full dataset Experiment  6  for MA : TEMA the MSE  is:  87.38626729945001
Stock with Full dataset Experiment  6  for MA : SMA the MAE is:  7.077228582293258
Stock with Full dataset Experiment  6  for MA : EMA the MAE is:  6.876111393338704
Stock with Full dataset Experiment  6  for MA : WMA the MAE is:  6.6664001460728475
Stock with Full dataset Experiment  6  for MA : DEMA the MAE is:  16.799244301034683
Stock with Full dataset Experiment  6  for MA : KAMA the MAE is:  8.510636158449836
Stock with Full dataset Experiment  6  for MA : MIDPOINT the MAE is:  8.251875922025462
Stock with Full dataset Experiment  6  for MA : T3 the MAE is:  10.12780101556255
Stock with Full dataset Experiment  6  for MA : TEMA the MAE is:  8.358174186376312
Stock with Full dataset Experiment  7  for MA : SMA the RMSE is:  6.682224873696692
Stock with Full dataset Experiment  7  for MA : EMA the RMSE is:  6.748320196113436
Stock with Full dataset Experiment  7  for MA : WMA the RMSE is:  6.504220199402522
Stock with Full dataset Experiment  7  for MA : DEMA the RMSE is:  4.827620751055335
Stock with Full dataset Experiment  7  for MA : KAMA the RMSE is:  4.252333670621163
Stock with Full dataset Experiment  7  for MA : MIDPOINT the RMSE is:  9.57069156727991
Stock with Full dataset Experiment  7  for MA : T3 the RMSE is:  12.049604131049065
Stock with Full dataset Experiment  7  for MA : TEMA the RMSE is:  6.412164328109044
Stock with Full dataset Experiment  7  for MA : SMA the MSE  is:  44.65212926265077
Stock with Full dataset Experiment  7  for MA : EMA the MSE  is:  45.539825469272486
Stock with Full dataset Experiment  7  for MA : WMA the MSE  is:  42.30488040231578
Stock with Full dataset Experiment  7  for MA : DEMA the MSE  is:  23.305922116020078
Stock with Full dataset Experiment  7  for MA : KAMA the MSE  is:  18.082341646298453
Stock with Full dataset Experiment  7  for MA : MIDPOINT the MSE  is:  91.59813707600279
Stock with Full dataset Experiment  7  for MA : T3 the MSE  is:  145.19295971499469
Stock with Full dataset Experiment  7  for MA : TEMA the MSE  is:  41.1158513706741
Stock with Full dataset Experiment  7  for MA : SMA the MAE is:  5.204686480071648
Stock with Full dataset Experiment  7  for MA : EMA the MAE is:  5.43245952292463
Stock with Full dataset Experiment  7  for MA : WMA the MAE is:  5.010195929360332
Stock with Full dataset Experiment  7  for MA : DEMA the MAE is:  3.7452201197397774
Stock with Full dataset Experiment  7  for MA : KAMA the MAE is:  3.4333194517527637
Stock with Full dataset Experiment  7  for MA : MIDPOINT the MAE is:  7.718313236319782
Stock with Full dataset Experiment  7  for MA : T3 the MAE is:  9.875885491811884
Stock with Full dataset Experiment  7  for MA : TEMA the MAE is:  5.720374187090847
Stock with Full dataset Experiment  8  for MA : SMA the RMSE is:  5.549231780992587
Stock with Full dataset Experiment  8  for MA : EMA the RMSE is:  5.689708043834667
Stock with Full dataset Experiment  8  for MA : WMA the RMSE is:  7.620210456276704
Stock with Full dataset Experiment  8  for MA : DEMA the RMSE is:  12.902399474280209
Stock with Full dataset Experiment  8  for MA : KAMA the RMSE is:  4.220769393485087
Stock with Full dataset Experiment  8  for MA : MIDPOINT the RMSE is:  4.303924496165662
Stock with Full dataset Experiment  8  for MA : T3 the RMSE is:  7.193936632248893
Stock with Full dataset Experiment  8  for MA : TEMA the RMSE is:  5.331498398524327
Stock with Full dataset Experiment  8  for MA : SMA the MSE  is:  30.79397335917816
Stock with Full dataset Experiment  8  for MA : EMA the MSE  is:  32.37277762407691
Stock with Full dataset Experiment  8  for MA : WMA the MSE  is:  58.067607397948805
Stock with Full dataset Experiment  8  for MA : DEMA the MSE  is:  166.4719121939062
Stock with Full dataset Experiment  8  for MA : KAMA the MSE  is:  17.81489427298047
Stock with Full dataset Experiment  8  for MA : MIDPOINT the MSE  is:  18.523766068694844
Stock with Full dataset Experiment  8  for MA : T3 the MSE  is:  51.75272426881254
Stock with Full dataset Experiment  8  for MA : TEMA the MSE  is:  28.424875173467463
Stock with Full dataset Experiment  8  for MA : SMA the MAE is:  4.345848876898189
Stock with Full dataset Experiment  8  for MA : EMA the MAE is:  4.4297291061987245
Stock with Full dataset Experiment  8  for MA : WMA the MAE is:  6.244282675104111
Stock with Full dataset Experiment  8  for MA : DEMA the MAE is:  11.649540302125361
Stock with Full dataset Experiment  8  for MA : KAMA the MAE is:  3.4008273908825086
Stock with Full dataset Experiment  8  for MA : MIDPOINT the MAE is:  3.4879205441290337
Stock with Full dataset Experiment  8  for MA : T3 the MAE is:  5.759673530885367
Stock with Full dataset Experiment  8  for MA : TEMA the MAE is:  4.66633698560039

Export HTML¶

from google.colab import drive
drive.mount('/content/drive')

Mounted at /content/drive

cd drive/MyDrive/Stock price prediction/Archana - LSTM Hybrid

/content/drive/.shortcut-targets-by-id/1IaGjVBlTspxI2CHSrxfYnaiYvsaG0pHs/Stock price prediction/Archana - LSTM Hybrid

%%shell
jupyter nbconvert --to html

	Unnamed: 0	Unnamed: 0.1	Unnamed: 0.1.1	Unnamed: 0.1.1.1	Open	High	Low	Close	Adj Close	Volume	MA7	MA21	MACD	20SD	upper_band	lower_band	EMA	logmomentum	absolute of 3 comp	angle of 3 comp	absolute of 6 comp	angle of 6 comp	absolute of 9 comp	angle of 9 comp	Date	search	COVID positiveIncrease	COVID deathIncrease	bull score	bear score	fourier bull 10	fourier bull 30	fourier bear 10	fourier bear 30
1592	1592	1781	1781	1781	150.199997	151.429993	150.059998	150.809998	150.809998	56787900.0	150.565717	148.423811	-1.137777	2.817933	154.059677	142.787944	150.767809	5.009368	93.428749	-0.061228	100.779503	-0.039111	103.599003	-0.022436	2021-11-09	19	112313	1258	0.119141	0.111328	NaN	NaN	NaN	NaN
1593	1593	1782	1782	1782	150.020004	150.130005	147.850006	147.919998	147.919998	65187100.0	150.417145	148.729049	-1.236913	2.144358	153.017766	144.440332	148.869268	4.989888	92.922909	-0.061683	99.694365	-0.039762	101.872301	-0.022657	2021-11-10	19	80301	1470	0.154297	0.109375	NaN	NaN	NaN	NaN
1594	1594	1783	1783	1783	148.960007	149.429993	147.679993	147.869995	147.869995	41000000.0	150.110001	149.060477	-1.165047	1.767475	152.595428	145.525526	148.203086	4.989548	92.416471	-0.062129	98.604584	-0.040391	100.137594	-0.022839	2021-11-11	19	94975	1662	0.102845	0.126915	NaN	NaN	NaN	NaN
1595	1595	1784	1784	1784	148.429993	150.399994	147.479996	149.990005	149.990005	63632600.0	149.895715	149.357144	-0.869308	1.420732	152.198608	146.515681	149.394365	5.003879	91.909483	-0.062566	97.510555	-0.040998	98.396260	-0.022980	2021-11-12	19	55499	797	0.157277	0.080595	NaN	NaN	NaN	NaN
1596	1596	1785	1785	1785	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2021-11-13	19	146529	2505	0.139459	0.083243	NaN	NaN	NaN	NaN
1597	1597	1786	1786	1786	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	2021-11-14	19	40964	479	0.151261	0.100840	NaN	NaN	NaN	NaN
1598	1598	1787	1787	1787	150.369995	151.880005	149.429993	150.000000	150.000000	59222800.0	149.758571	149.602859	-0.907641	1.229694	152.062246	147.143471	149.798122	5.003946	91.401994	-0.062993	96.412672	-0.041581	96.649685	-0.023077	2021-11-15	22	30290	148	0.136737	0.109389	NaN	NaN	NaN	NaN
1599	1599	1788	1788	1788	149.940002	151.490005	149.339996	151.000000	151.000000	59256200.0	149.718571	149.814763	-0.791320	1.236243	152.287250	147.342277	150.599374	5.010635	90.894052	-0.063410	95.311334	-0.042140	94.899260	-0.023130	2021-11-16	22	138962	1294	0.135531	0.115385	NaN	NaN	NaN	NaN
1600	1600	1789	1789	1789	151.000000	155.000000	150.990005	153.490005	153.490005	88807000.0	150.154286	150.040002	-0.657719	1.467121	152.974245	147.105759	152.526461	5.027099	90.385704	-0.063817	94.206941	-0.042673	93.146378	-0.023135	2021-11-17	22	87626	1290	0.100870	0.126957	NaN	NaN	NaN	NaN
1601	1601	1790	1790	1790	153.710007	158.669998	153.050003	157.869995	157.869995	137659100.0	151.162857	150.450002	-0.609656	2.267825	154.985653	145.914351	156.088817	5.055417	89.877000	-0.064214	93.099895	-0.043179	91.392433	-0.023090	2021-11-18	22	111404	1637	0.145098	0.121569	NaN	NaN	NaN	NaN

	Unnamed: 0	Unnamed: 0.1	Unnamed: 0.1.1	Unnamed: 0.1.1.1	Open	High	Low	Close	Adj Close	Volume	MA7	MA21	MACD	20SD	upper_band	lower_band	EMA	logmomentum	absolute of 3 comp	angle of 3 comp	absolute of 6 comp	angle of 6 comp	absolute of 9 comp	angle of 9 comp	Date	search	bull score	bear score	fourier bull 10	fourier bull 30	fourier bear 10	fourier bear 30
2	2	191	191	191	36.220001	36.325001	35.775002	35.875000	34.054882	57111200.0	36.173571	36.751904	0.303356	0.960520	38.672945	34.830864	35.924548	3.551770	38.458011	0.046984	29.704545	0.102857	43.304973	-0.053955	2017-07-03	15	0.666667	0.000000	0.142778	0.146810	0.100537	0.099251
4	4	193	193	193	35.922501	36.197498	35.680000	36.022499	34.194897	86278400.0	36.095357	36.634762	0.328795	0.852735	38.340231	34.929292	35.989849	3.555991	38.240991	0.049445	29.954520	0.099254	43.438321	-0.053936	2017-07-05	15	0.400000	0.000000	0.144487	0.145833	0.100630	0.096361
5	5	194	194	194	35.755001	35.875000	35.602501	35.682499	33.872143	96515200.0	35.984999	36.495238	0.346702	0.677629	37.850495	35.139980	35.784949	3.546235	38.027974	0.051918	30.209839	0.095602	43.557403	-0.053820	2017-07-06	15	0.142857	0.142857	0.145346	0.145164	0.100672	0.094761
6	6	195	195	195	35.724998	36.187500	35.724998	36.044998	34.216255	76806800.0	36.001071	36.362023	0.387422	0.387634	37.137291	35.586756	35.958315	3.556633	37.818962	0.054401	30.470232	0.091907	43.662260	-0.053608	2017-07-07	15	0.333333	0.000000	0.146208	0.144377	0.100711	0.093072
9	9	198	198	198	36.027500	36.487499	35.842499	36.264999	34.425095	84362400.0	35.973571	36.243809	0.388315	0.308042	36.859893	35.627725	36.162771	3.562891	37.613953	0.056893	30.735430	0.088177	43.752965	-0.053302	2017-07-10	14	0.000000	0.000000	0.148802	0.141354	0.100808	0.087587

	Open	High	Low	Close	Adj Close	Volume	MA7	MA21	MACD	20SD	upper_band	lower_band	EMA	logmomentum	absolute of 3 comp	angle of 3 comp	absolute of 6 comp	angle of 6 comp	absolute of 9 comp	angle of 9 comp	Date	search	bull score	bear score	fourier bull 10	fourier bull 30	fourier bear 10	fourier bear 30
2	36.220001	36.325001	35.775002	35.875000	34.054882	57111200.0	36.173571	36.751904	0.303356	0.960520	38.672945	34.830864	35.924548	3.551770	38.458011	0.046984	29.704545	0.102857	43.304973	-0.053955	2017-07-03	15	0.666667	0.000000	0.142778	0.146810	0.100537	0.099251
4	35.922501	36.197498	35.680000	36.022499	34.194897	86278400.0	36.095357	36.634762	0.328795	0.852735	38.340231	34.929292	35.989849	3.555991	38.240991	0.049445	29.954520	0.099254	43.438321	-0.053936	2017-07-05	15	0.400000	0.000000	0.144487	0.145833	0.100630	0.096361
5	35.755001	35.875000	35.602501	35.682499	33.872143	96515200.0	35.984999	36.495238	0.346702	0.677629	37.850495	35.139980	35.784949	3.546235	38.027974	0.051918	30.209839	0.095602	43.557403	-0.053820	2017-07-06	15	0.142857	0.142857	0.145346	0.145164	0.100672	0.094761
6	35.724998	36.187500	35.724998	36.044998	34.216255	76806800.0	36.001071	36.362023	0.387422	0.387634	37.137291	35.586756	35.958315	3.556633	37.818962	0.054401	30.470232	0.091907	43.662260	-0.053608	2017-07-07	15	0.333333	0.000000	0.146208	0.144377	0.100711	0.093072
9	36.027500	36.487499	35.842499	36.264999	34.425095	84362400.0	35.973571	36.243809	0.388315	0.308042	36.859893	35.627725	36.162771	3.562891	37.613953	0.056893	30.735430	0.088177	43.752965	-0.053302	2017-07-10	14	0.000000	0.000000	0.148802	0.141354	0.100808	0.087587

	Open	High	Low	Close	Adj Close	Volume	MA7	MA21	MACD	20SD	upper_band	lower_band	EMA	logmomentum	absolute of 3 comp	angle of 3 comp	absolute of 6 comp	angle of 6 comp	absolute of 9 comp	angle of 9 comp	Date	search	bull score	bear score	fourier bull 10	fourier bull 30	fourier bear 10	fourier bear 30
2	36.220001	36.325001	35.775002	35.875000	34.054882	57111200.0	36.173571	36.751904	0.303356	0.960520	38.672945	34.830864	35.924548	3.551770	38.458011	0.046984	29.704545	0.102857	43.304973	-0.053955	2017-07-03	15	0.666667	0.000000	0.142778	0.146810	0.100537	0.099251
4	35.922501	36.197498	35.680000	36.022499	34.194897	86278400.0	36.095357	36.634762	0.328795	0.852735	38.340231	34.929292	35.989849	3.555991	38.240991	0.049445	29.954520	0.099254	43.438321	-0.053936	2017-07-05	15	0.400000	0.000000	0.144487	0.145833	0.100630	0.096361
5	35.755001	35.875000	35.602501	35.682499	33.872143	96515200.0	35.984999	36.495238	0.346702	0.677629	37.850495	35.139980	35.784949	3.546235	38.027974	0.051918	30.209839	0.095602	43.557403	-0.053820	2017-07-06	15	0.142857	0.142857	0.145346	0.145164	0.100672	0.094761
6	35.724998	36.187500	35.724998	36.044998	34.216255	76806800.0	36.001071	36.362023	0.387422	0.387634	37.137291	35.586756	35.958315	3.556633	37.818962	0.054401	30.470232	0.091907	43.662260	-0.053608	2017-07-07	15	0.333333	0.000000	0.146208	0.144377	0.100711	0.093072
9	36.027500	36.487499	35.842499	36.264999	34.425095	84362400.0	35.973571	36.243809	0.388315	0.308042	36.859893	35.627725	36.162771	3.562891	37.613953	0.056893	30.735430	0.088177	43.752965	-0.053302	2017-07-10	14	0.000000	0.000000	0.148802	0.141354	0.100808	0.087587

	Open	High	Low	Close	Adj Close	Volume	MA7	MA21	MACD	20SD	upper_band	lower_band	EMA	logmomentum	absolute of 3 comp	angle of 3 comp	absolute of 6 comp	angle of 6 comp	absolute of 9 comp	angle of 9 comp	search	bull score	bear score	fourier bull 10	fourier bull 30	fourier bear 10	fourier bear 30
2017-07-03	36.220001	36.325001	35.775002	35.875000	34.054882	57111200.0	36.173571	36.751904	0.303356	0.960520	38.672945	34.830864	35.924548	3.551770	38.458011	0.046984	29.704545	0.102857	43.304973	-0.053955	15	0.666667	0.000000	0.142778	0.146810	0.100537	0.099251
2017-07-05	35.922501	36.197498	35.680000	36.022499	34.194897	86278400.0	36.095357	36.634762	0.328795	0.852735	38.340231	34.929292	35.989849	3.555991	38.240991	0.049445	29.954520	0.099254	43.438321	-0.053936	15	0.400000	0.000000	0.144487	0.145833	0.100630	0.096361
2017-07-06	35.755001	35.875000	35.602501	35.682499	33.872143	96515200.0	35.984999	36.495238	0.346702	0.677629	37.850495	35.139980	35.784949	3.546235	38.027974	0.051918	30.209839	0.095602	43.557403	-0.053820	15	0.142857	0.142857	0.145346	0.145164	0.100672	0.094761
2017-07-07	35.724998	36.187500	35.724998	36.044998	34.216255	76806800.0	36.001071	36.362023	0.387422	0.387634	37.137291	35.586756	35.958315	3.556633	37.818962	0.054401	30.470232	0.091907	43.662260	-0.053608	15	0.333333	0.000000	0.146208	0.144377	0.100711	0.093072
2017-07-10	36.027500	36.487499	35.842499	36.264999	34.425095	84362400.0	35.973571	36.243809	0.388315	0.308042	36.859893	35.627725	36.162771	3.562891	37.613953	0.056893	30.735430	0.088177	43.752965	-0.053302	14	0.000000	0.000000	0.148802	0.141354	0.100808	0.087587

	period	SMA	EMA	WMA	DEMA	KAMA	MIDPOINT	T3	TEMA	TRIMA
0	4	2.272452	2.652772	2.896972	3.800351	2.299585	2.171369	1.978458	4.609342	2.411225
1	5	1.839451	2.355815	2.481058	3.327525	1.841282	1.826597	1.640277	4.262302	1.994382
2	6	1.583886	2.159532	2.194320	2.945924	1.536136	1.605787	1.510972	3.878845	1.679710
3	7	1.461290	2.026758	1.990629	2.651927	1.506197	1.558096	1.514015	3.510432	1.486348
4	8	1.447516	1.935302	1.853935	2.429648	1.509566	1.621595	1.601580	3.184123	1.373337

	open	high	low	close	Adj Close	volume	MA7	MA21	MACD	20SD	upper_band	lower_band	EMA	logmomentum	absolute of 3 comp	angle of 3 comp	absolute of 6 comp	angle of 6 comp	absolute of 9 comp	angle of 9 comp	search
1060	140.200839	141.942909	138.524500	140.171495	139.966842	8.852448e+07	142.165478	146.699207	1.815578	4.572948	155.845103	137.553312	140.365562	4.935800	105.739092	-0.047411	125.318767	-0.018291	140.471430	-0.008749	19.573385
1061	139.425914	141.705469	138.035200	140.698014	140.492650	8.620711e+07	141.528981	145.978836	2.115887	4.189393	154.357621	137.600050	140.587196	4.939545	105.263514	-0.048037	124.464999	-0.019222	139.335869	-0.009472	19.632022
1062	140.773058	142.636405	139.932338	141.733666	141.526843	7.421445e+07	141.294887	145.298477	2.211018	3.647690	152.593858	138.003097	141.351509	4.946870	104.786174	-0.048658	123.598217	-0.020150	138.164839	-0.010188	19.698090
1063	142.179695	143.266994	141.127848	142.249061	142.041527	6.519616e+07	141.224295	144.665584	2.093072	3.241276	151.148137	138.183031	141.949877	4.950518	104.307114	-0.049275	122.718682	-0.021074	136.959041	-0.010898	19.763505
1064	142.253947	144.008334	141.546689	142.555532	142.347589	6.254214e+07	141.336839	144.184381	1.988881	2.884864	149.954110	138.414652	142.353647	4.952685	103.826381	-0.049886	121.826667	-0.021994	135.719217	-0.011600	20.311676
1065	142.782738	143.732491	141.438660	142.125353	141.918068	6.542511e+07	141.385297	143.758659	1.774804	2.626682	149.012024	138.505294	142.201451	4.949632	103.344020	-0.050491	120.922446	-0.022909	134.446150	-0.012293	20.671514
1066	142.153085	142.656915	140.466684	141.564232	141.357788	7.040262e+07	141.585336	143.387397	1.634667	2.376817	148.141030	138.633764	141.776638	4.945637	102.860075	-0.051092	120.006305	-0.023818	133.140665	-0.012977	20.900131
1067	142.177201	143.194327	140.977156	142.610382	142.402435	6.948112e+07	141.933749	143.094536	1.573317	2.074153	147.242842	138.946230	142.332468	4.953023	102.374593	-0.051687	119.078535	-0.024722	131.803627	-0.013650	21.038585
1068	143.009006	144.052615	142.286776	143.812497	143.602819	6.805244e+07	142.378675	142.879716	1.473333	1.874158	146.628032	139.131400	143.319154	4.961467	101.887619	-0.052275	118.139433	-0.025618	130.435938	-0.014311	21.116168
1069	143.380322	145.547752	142.940349	145.397429	145.185452	7.592729e+07	142.902069	142.813890	1.447641	1.844159	146.502207	139.125573	144.704671	4.972505	101.399198	-0.052858	117.189304	-0.026508	129.038540	-0.014959	21.153587
1070	145.337970	147.615882	144.980528	147.444584	147.229635	7.653090e+07	143.644287	142.961273	1.284466	2.010227	146.981728	138.940819	146.531280	4.986604	100.909377	-0.053435	116.228458	-0.027389	127.612408	-0.015592	21.165321
1071	147.375283	149.163050	146.995423	148.921380	148.704294	6.811986e+07	144.553694	143.236380	0.961952	2.270386	147.777152	138.695607	148.124680	4.996737	100.418203	-0.054006	115.257214	-0.028261	126.158555	-0.016211	21.161363
1072	148.656821	150.010875	148.071943	149.870634	149.652170	6.425222e+07	145.660163	143.530869	0.589081	2.556352	148.643574	138.418164	149.288649	5.003230	99.925720	-0.054570	114.275894	-0.029124	124.678027	-0.016812	21.148490
1073	149.806550	150.715254	149.026204	149.977942	149.759331	6.069918e+07	146.862121	143.785380	0.135134	2.805932	149.397244	138.173516	149.748178	5.003989	99.431976	-0.055128	113.284828	-0.029977	123.171903	-0.017396	21.131204
1074	149.937482	150.666013	149.022091	149.911667	149.693162	5.465321e+07	147.905162	144.001463	-0.245163	3.045742	150.092948	137.909978	149.857170	5.003545	98.937018	-0.055679	112.284350	-0.030820	121.641290	-0.017961	25.016406
1075	150.228161	151.254072	149.586503	150.104281	149.885502	5.602702e+07	148.803988	144.237215	-0.571069	3.270011	150.777237	137.697192	150.021910	5.004835	98.440892	-0.056223	111.274800	-0.031650	120.087330	-0.018506	27.455491
1076	150.328251	150.997797	149.591175	149.912656	149.694163	5.484778e+07	149.449021	144.548659	-0.850904	3.458615	151.465890	137.631428	149.949074	5.003520	97.943645	-0.056759	110.256524	-0.032469	118.511190	-0.019029	28.912854
1077	150.525566	152.430694	150.099878	151.531571	151.310718	7.580033e+07	150.032876	144.967153	-0.975625	3.719924	152.407001	137.527305	151.004072	5.014296	97.445324	-0.057289	109.229873	-0.033274	116.914063	-0.019528	29.716707
1078	149.301052	151.688142	148.723104	151.137179	150.916905	1.012990e+08	150.349418	145.413317	-0.891585	3.905336	153.223988	137.602646	151.092810	5.011652	96.945977	-0.057811	108.195203	-0.034066	115.297171	-0.020004	30.096629
1079	149.321425	151.018197	148.455004	150.396057	150.176865	9.262134e+07	150.424479	145.823313	-0.852689	3.878291	153.579894	138.066731	150.628308	5.006660	96.445650	-0.058325	107.152874	-0.034844	113.661756	-0.020453	27.283213